Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

ok this is a fcking cheat code for coding agents how to make them 200x faster and 400x cheaper with Jev engineering Jev founder Diogo Amogo put the whole harness into a 12-page PDF, 10 steps: 1. meet Jev the LLM writes, the harness executes, Jev decides what each... turn sees, where it routes and whether it runs 2. ask the question that breaks every agent how would you build one if LLMs had no KV cache? 3. quit blind routing Claude Opus 5.5 -> Sonnet 5.5 -> Opus costs 6.19, Opus alone 4.15, because every handoff reprocesses the full context 4. follow the tokens reading and searching eat 56.2% of tool turns and 46.5% of tokens, writing code stays under 10% 5. score each chunk per query hide it, summarize it or keep it whole, and compress once the question is known 6. reveal tools in tiers one-line snippets for hundreds of tools, full schema on demand 7. load instructions by condition a .tsx edit pulls the style guide, billing/ pulls its gotchas file, compaction can't wipe either 8. route by trust as well as difficulty secrets and infra stay on first-party frontier models, public docs go to the cheapest one 9. reuse one retrieval pass review, evals, explainers and progress pages all run read-only in the background 10. gate every command allow / ask / deny policies read the whole script before it runs hand this PDF and the article below to Claude Code or Codex and start shipping fastershow more

Mr. Buzzoni

25,872 subscribers

17,457 views • 2 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

15 Comments

Jackal Killu1 day ago

200x faster and 400x cheaper in the same sentence is the tell 💀 real harness gains come from context control, not magic multipliers. the "Jev decides what each turn sees" line is the only part that actually matters here

Hussain Hashim | Building SundayBack1 day ago

@polydao nice, but watch out for overfitting on smaller tasks. sometimes the harness holds too tight and misses edge cases. found that out the hard way!

Brjan | AI Builder1 day ago

if Jev can really boost efficiency like that, it'll change the game for devs

Harley Lewis Foote1 day ago

The harness-LLM separation is elegant. Execution without generation bloat.

Cupsey1 day ago

wait reading/searching burns 56% of the tokens and writing stays under 10%?

Chen1 day ago

12 pages for a 200x faster coding agent hack? that's a surprisingly small read for that big of a claim.

magsimich1 day ago

That is really focking gold man

Yohaku2 days ago

thanks for the alpha my bro 🫶

Lorden1 day ago

i made a similar list recently buddy you should check it out

王也弱1 day ago

我看到过好多在推荐这篇文章的人，真的有人用过吗？我并不觉得他最后的结果会好。

Sarah Satonov1 day ago

200x faster and 400x cheaper is wild if it holds up. the "harness decides what each turn sees" part is the real unlock, context control beats raw model size

DHRUV BANSAL1 day ago

A lot of these steps change what the model sees before it answers and none of that shows up in the diff. A month later you have the code. No record of which chunk got hidden or which model it went to, the agent can't tell you either

Sophia p.1 day ago

Interesting perspective

P. I.1 day ago

Step 1 is the whole trick: let the cheap model say no so the expensive one never has to.

Issa1 day ago

Interesting claim - any data backign the 200x speed claim?

Related Videos

Jev’s founder just dropped the 12-page harness that makes coding agents 400× cheaper the first thing it shows: your agent spends under 10% of its tokens actually writing code → reading and searching take 56.2% of tool turns and 46.5% of tokens. that’s where the money goes → routing Opus → Sonnet → Opus to save costs 6.19. pure Opus costs 4.15. every handoff reprocesses the whole context → compress after the question, never before. every chunk gets scored: hide, short summary, long summary or full → instructions load by condition. touch *.tsx and the style guide loads. touch billing/ and its gotchas file loads. compaction can’t erase either → route by trust, not difficulty. secrets and infra stay on first-party frontier models, public docs go to the cheapest one → every command passes an allow / ask / deny policy that reads the script before it runs. not just its name their claim: 200× faster, 400× cheaper drop the PDF into Claude Code or Codex and let it rebuild your harness ↓

Jev’s founder just dropped the 12-page harness that makes coding agents 400× cheaper the first thing it shows: your agent spends under 10% of its tokens actually writing code → reading and searching take 56.2% of tool turns and 46.5% of tokens. that’s where the money goes → routing Opus → Sonnet → Opus to save costs 6.19. pure Opus costs 4.15. every handoff reprocesses the whole context → compress after the question, never before. every chunk gets scored: hide, short summary, long summary or full → instructions load by condition. touch *.tsx and the style guide loads. touch billing/ and its gotchas file loads. compaction can’t erase either → route by trust, not difficulty. secrets and infra stay on first-party frontier models, public docs go to the cheapest one → every command passes an allow / ask / deny policy that reads the script before it runs. not just its name their claim: 200× faster, 400× cheaper drop the PDF into Claude Code or Codex and let it rebuild your harness ↓

Carnage

61,361 views • 13 days ago

Jev founder, Diogo Almeida, just put out a PDF on building a Jev harness for coding agents the claim: 200x faster, 400x cheaper the model stopped being the bottleneck a while ago. the harness around it is where the cost and the speed actually live five decisions sit on every loop, and only one of them writes code hand this PDF and the article below to your Claude Code or Codex instance and let it rebuild its own setup your agent gets a better harness tonight, and monday looks different than it would have 👇

Jev founder, Diogo Almeida, just put out a PDF on building a Jev harness for coding agents the claim: 200x faster, 400x cheaper the model stopped being the bottleneck a while ago. the harness around it is where the cost and the speed actually live five decisions sit on every loop, and only one of them writes code hand this PDF and the article below to your Claude Code or Codex instance and let it rebuild its own setup your agent gets a better harness tonight, and monday looks different than it would have 👇

Hanako

37,887 views • 10 days ago

Jev + Opus 5.5: Anthropic's new model beats GPT-6 Astra for 1/5 the cost, and 4 API changes will 400 your agent before it writes a single line I pulled these 10 steps from the migration docs so you don't learn them in production step 1 → $4 / $20 per 1M. Opus 5 was $5 / $25. cache reads dropped from $0.50 to $0.20 step 2 → 66.4% on Terminal-Bench 4.0 vs GPT-6 Astra 57.9% and Opus 5 52.3%. +14.1 points in one release, and on FrontierCode it beats Astra at default effort for 1/5 the cost step 3 → thinking can't be turned off anymore. send thinking: disabled and you get a 400. drop the field, set effort step 4 → tool_choice any and tool are gone. 400. switch to auto + strict step 5 → edit anything above a thinking block and the request dies. append only, or opt into drop_block step 6 → computer_20251124 is dead on the API. 400. move to computer_toolset_20260801 step 7 → the quiet one: default effort fell from high to medium. your agent thinks less than you set it up to and nothing tells you step 8 → hop Opus 5.5 → Sonnet 5 → Opus 5.5 and you pay 4.36 instead of 3.32. +31%, the cache dies and Sonnet can't read Opus's reasoning step 9 → change effort at the top of the request and the cache is gone. Jev sets it per message and the cache stays step 10 → switch fast - standard mid-session and it's a full cache miss. Jev picks speed once, on turn one one model, three knobs, zero 400s. that is Jev + Opus 5.5 send this to your Claude Code before you touch the model ID, then read my full Jev deep dive in the article below ↓

Jev + Opus 5.5: Anthropic's new model beats GPT-6 Astra for 1/5 the cost, and 4 API changes will 400 your agent before it writes a single line I pulled these 10 steps from the migration docs so you don't learn them in production step 1 → $4 / $20 per 1M. Opus 5 was $5 / $25. cache reads dropped from $0.50 to $0.20 step 2 → 66.4% on Terminal-Bench 4.0 vs GPT-6 Astra 57.9% and Opus 5 52.3%. +14.1 points in one release, and on FrontierCode it beats Astra at default effort for 1/5 the cost step 3 → thinking can't be turned off anymore. send thinking: disabled and you get a 400. drop the field, set effort step 4 → tool_choice any and tool are gone. 400. switch to auto + strict step 5 → edit anything above a thinking block and the request dies. append only, or opt into drop_block step 6 → computer_20251124 is dead on the API. 400. move to computer_toolset_20260801 step 7 → the quiet one: default effort fell from high to medium. your agent thinks less than you set it up to and nothing tells you step 8 → hop Opus 5.5 → Sonnet 5 → Opus 5.5 and you pay 4.36 instead of 3.32. +31%, the cache dies and Sonnet can't read Opus's reasoning step 9 → change effort at the top of the request and the cache is gone. Jev sets it per message and the cache stays step 10 → switch fast - standard mid-session and it's a full cache miss. Jev picks speed once, on turn one one model, three knobs, zero 400s. that is Jev + Opus 5.5 send this to your Claude Code before you touch the model ID, then read my full Jev deep dive in the article below ↓

Carnage

16,674 views • 12 days ago

ANTHROPIC LEAKED A $4.2M FILE WHERE 4 AGENTS BUILD THE JEV SYSTEM IN 60 MINUTES, DOING $100K A MONTH four agents cost $0, and the system they assemble in an hour generates $100K a month scout → builder → critic → operator → JEV every agent is pinned to one exact model version, and none of them runs on "latest" the scout on Haiku 4.5 reads the market, the builder on Sonnet 5 builds everything, the critic on Opus 5 decides what ships the operator runs Haiku through the batch API at half price - the one agent that never has to hurry the builder takes 59% of the whole hour, because it's the one writing, and writing costs 5x more than reading short answers are cheap answers - and the whole economics rests on that one rule pin the versions in ROOT.md and next month JEV behaves exactly the same point it at "latest" and the model underneath updates quietly, no error, and the answers start to drift $100K a month is 334 customers at $299 four versions, one system - pin them and JEV stays JEV save this and paste it into Claude Code - let it build you these 4 agents ↓

ANTHROPIC LEAKED A $4.2M FILE WHERE 4 AGENTS BUILD THE JEV SYSTEM IN 60 MINUTES, DOING $100K A MONTH four agents cost $0, and the system they assemble in an hour generates $100K a month scout → builder → critic → operator → JEV every agent is pinned to one exact model version, and none of them runs on "latest" the scout on Haiku 4.5 reads the market, the builder on Sonnet 5 builds everything, the critic on Opus 5 decides what ships the operator runs Haiku through the batch API at half price - the one agent that never has to hurry the builder takes 59% of the whole hour, because it's the one writing, and writing costs 5x more than reading short answers are cheap answers - and the whole economics rests on that one rule pin the versions in ROOT.md and next month JEV behaves exactly the same point it at "latest" and the model underneath updates quietly, no error, and the answers start to drift $100K a month is 334 customers at $299 four versions, one system - pin them and JEV stays JEV save this and paste it into Claude Code - let it build you these 4 agents ↓

Sprytix

37,977 views • 13 days ago

$this harness stack is f*cking gold TypeSafe AI + LangChain finally dropped the layer that makes agents affordable at company scale: jev running inside the langchain agent loop as middleware the problem every big team hits: each fork in the loop is another full LLM call. at 10 agents that's a bill. at 10,000 it's the budget > routing before: every task goes to the frontier model now: jev picks the least costly model that can finish it. lookups go fast, architecture goes powerful > guardrails before: the "is this command dangerous?" check sat in the closed parts of claude code, codex, cursor now: AutoModeMiddleware(tools=["bash"]). one line, any agent, blocked before the tool runs > decisions before: one LLM call per question now: every question about the same state in one request, answered in parallel > audit before: "the model decided" now: the answer, the probability and the confidence stay in agent state > adoption no rewrite. pip install langchain-typesafe and drop it into the agent you already run TypeSafe reports up to 200x faster inference and 400x lower cost than comparable LLMs on classification. the LLM still reasons and writes. jev takes the thousands of small calls in between already live: browserbase agents for fractions of a cent, a live trading agent, email triage at scale full loop mapped below: 7 agents, 4 jev gates per step count the forks in your agent loop tonigh$

this harness stack is f*cking gold TypeSafe AI + LangChain finally dropped the layer that makes agents affordable at company scale: jev running inside the langchain agent loop as middleware the problem every big team hits: each fork in the loop is another full LLM call. at 10 agents that's a bill. at 10,000 it's the budget > routing before: every task goes to the frontier model now: jev picks the least costly model that can finish it. lookups go fast, architecture goes powerful > guardrails before: the "is this command dangerous?" check sat in the closed parts of claude code, codex, cursor now: AutoModeMiddleware(tools=["bash"]). one line, any agent, blocked before the tool runs > decisions before: one LLM call per question now: every question about the same state in one request, answered in parallel > audit before: "the model decided" now: the answer, the probability and the confidence stay in agent state > adoption no rewrite. pip install langchain-typesafe and drop it into the agent you already run TypeSafe reports up to 200x faster inference and 400x lower cost than comparable LLMs on classification. the LLM still reasons and writes. jev takes the thousands of small calls in between already live: browserbase agents for fractions of a cent, a live trading agent, email triage at scale full loop mapped below: 7 agents, 4 jev gates per step count the forks in your agent loop tonigh

NO1ennn

31,666 views • 5 days ago

this is pure f*cking gold for anyone running coding agents Jev founder, Diogo Almeida, wrote a guide on building a Jev harness the expensive model only writes the code. every fork around it goes to Jev the bill: > 6,000 forks a day on a frontier model: $180 > the same 6,000 forks on Jev: $0.25 > the whole harness, patches included: about $24 99 percent of what's left is the code itself, which is the only part you should be paying for what's inside: > the turn snapshot, five hooks, the cascade > thresholds read off your own receipts > the one rule a model never gets a vote on one evening of setup and your agent stops paying frontier prices to answer yes or no ↓

this is pure f*cking gold for anyone running coding agents Jev founder, Diogo Almeida, wrote a guide on building a Jev harness the expensive model only writes the code. every fork around it goes to Jev the bill: > 6,000 forks a day on a frontier model: $180 > the same 6,000 forks on Jev: $0.25 > the whole harness, patches included: about $24 99 percent of what's left is the code itself, which is the only part you should be paying for what's inside: > the turn snapshot, five hooks, the cascade > thresholds read off your own receipts > the one rule a model never gets a vote on one evening of setup and your agent stops paying frontier prices to answer yes or no ↓

Hanako

20,837 views • 7 days ago

Claude Code tip: once Opus 5.5 runs your main session, stop leaving Fable 5.1 on the bench put it on call with /advisor run /advisor fable Opus 5.5 keeps writing the code Fable 5.1 reads the whole session, every tool call included, and only speaks up at three moments: → before a plan: is this the right approach? → when the same error comes back: am I digging in the wrong place? → before "done": what did I miss? Fable 5.1 reviews. Opus 5.5 ships jev engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to jev in under half a second, and the big model only sees the ones that split - the full tree > Opus 5.5 on high runs the main session > explorer reads the code > worker edits and runs tests > researcher pulls the docs > all three on medium > Fable 5.1 on call as the advisor paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Check ~/.claude/agents and .claude/agents for subagents that already fit explorer, worker and researcher. > Draft new ones only for missing roles > Give each model: opus, effort: medium > Skip any that pin a different model and list them 2. Set the main session to high via effortLevel in ~/.claude/settings.json, and set advisorModel to fable 3. Find anything that keeps the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, any variable that stops feature-flag fetching) plus CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report them, change nothing 4. Add one rule to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done Show me every change as a diff first. No edits until I say go." ↳

Claude Code tip: once Opus 5.5 runs your main session, stop leaving Fable 5.1 on the bench put it on call with /advisor run /advisor fable Opus 5.5 keeps writing the code Fable 5.1 reads the whole session, every tool call included, and only speaks up at three moments: → before a plan: is this the right approach? → when the same error comes back: am I digging in the wrong place? → before "done": what did I miss? Fable 5.1 reviews. Opus 5.5 ships jev engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to jev in under half a second, and the big model only sees the ones that split - the full tree > Opus 5.5 on high runs the main session > explorer reads the code > worker edits and runs tests > researcher pulls the docs > all three on medium > Fable 5.1 on call as the advisor paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Check ~/.claude/agents and .claude/agents for subagents that already fit explorer, worker and researcher. > Draft new ones only for missing roles > Give each model: opus, effort: medium > Skip any that pin a different model and list them 2. Set the main session to high via effortLevel in ~/.claude/settings.json, and set advisorModel to fable 3. Find anything that keeps the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, any variable that stops feature-flag fetching) plus CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report them, change nothing 4. Add one rule to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done Show me every change as a diff first. No edits until I say go." ↳

Hanako

51,329 views • 4 days ago

Finally, an OpenRouter for agent harnesses! (including System One by Jev) Devs just open-sourced a plug-and-play infrastructure layer that lets you run any harness under a single interface, like: - Codex - Hermes - Claude code - DeepSeek Harness - System One, powered by Jev - And 9 more agent harnesses This means you can bring Jev into the same product that already uses Codex, Claude Code, or another supported harness, without writing another implementation for sessions, streaming, files, cancellation, and failure handling. Here's the repo: (don't forget to star it ⭐ ) The harnesses run locally, and the Unified Harness Protocol (UHP) defines the common task interface with an OpenAI Responses-compatible API. If you want to dive deeper, my recent article explains why model routing is not the same as harness routing, and what it takes to support multiple harnesses. It also covers UHP, the full local setup, a working API call, and how sessions and files work. Read it below.

Finally, an OpenRouter for agent harnesses! (including System One by Jev) Devs just open-sourced a plug-and-play infrastructure layer that lets you run any harness under a single interface, like: - Codex - Hermes - Claude code - DeepSeek Harness - System One, powered by Jev - And 9 more agent harnesses This means you can bring Jev into the same product that already uses Codex, Claude Code, or another supported harness, without writing another implementation for sessions, streaming, files, cancellation, and failure handling. Here's the repo: (don't forget to star it ⭐ ) The harnesses run locally, and the Unified Harness Protocol (UHP) defines the common task interface with an OpenAI Responses-compatible API. If you want to dive deeper, my recent article explains why model routing is not the same as harness routing, and what it takes to support multiple harnesses. It also covers UHP, the full local setup, a working API call, and how sessions and files work. Read it below.

Akshay 🚀

355,545 views • 14 days ago

Claude Code tip: keep Opus 5.5 as your main model, but stop paying Opus prices for your subagents move them to Sonnet 5.5 Opus 5.5 plans and decides Sonnet 5.5 subagents do the heavy reading, editing and testing at half the price ($2 / $10 vs $4 / $20 per 1M tokens) Fable 5.1 stays on call with /advisor and only speaks up at three points: → before a plan: is this the right approach? → when the same error comes back: am I digging in the wrong place? → before "done": what did I miss? Opus thinks. Sonnet does. Fable checks Jev engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to Jev in under half a second, and the big models only see the ones that split - the full tree > Opus 5.5 on high runs the main session > explorer reads the code > worker edits and runs tests > researcher pulls the docs > all three on Sonnet 5.5, medium > Fable 5.1 on call as the advisor paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Check ~/.claude/agents and .claude/agents for subagents that already fit explorer, worker and researcher. > Draft new ones only for missing roles > Give each model: claude-sonnet-5-5, effort: medium > List any that pin a different model before changing them 2. Keep the main session on Opus, set effortLevel to high in ~/.claude/settings.json and advisorModel to fable 3. Find anything that keeps the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, any variable that stops feature-flag fetching) plus CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report them, change nothing 4. Add one rule to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done Show me every change as a diff first. No edits until I say go." ↳

Claude Code tip: keep Opus 5.5 as your main model, but stop paying Opus prices for your subagents move them to Sonnet 5.5 Opus 5.5 plans and decides Sonnet 5.5 subagents do the heavy reading, editing and testing at half the price ($2 / $10 vs $4 / $20 per 1M tokens) Fable 5.1 stays on call with /advisor and only speaks up at three points: → before a plan: is this the right approach? → when the same error comes back: am I digging in the wrong place? → before "done": what did I miss? Opus thinks. Sonnet does. Fable checks Jev engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to Jev in under half a second, and the big models only see the ones that split - the full tree > Opus 5.5 on high runs the main session > explorer reads the code > worker edits and runs tests > researcher pulls the docs > all three on Sonnet 5.5, medium > Fable 5.1 on call as the advisor paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Check ~/.claude/agents and .claude/agents for subagents that already fit explorer, worker and researcher. > Draft new ones only for missing roles > Give each model: claude-sonnet-5-5, effort: medium > List any that pin a different model before changing them 2. Keep the main session on Opus, set effortLevel to high in ~/.claude/settings.json and advisorModel to fable 3. Find anything that keeps the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, any variable that stops feature-flag fetching) plus CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report them, change nothing 4. Add one rule to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done Show me every change as a diff first. No edits until I say go." ↳

delost

27,459 views • 3 days ago

Jev is WILD for SEO audit 🤯 in 45.1 seconds it read all 586 pages on my site and rebuilt the internal link map. 584 links placed, 139 pages it refused to link because nothing honestly fit. total cost $0.21. Claude Opus 5, same 586 pages, same clock, got through 21 of them and spent $1.43. per page that is ~190x cheaper. the full Opus pass would have run $43. internal linking is the perfect Jev job. it is not writing, it is 8,790 yes/no calls: does this page have a real reason to link to that one, and is there anchor text already sitting in the copy. that is a classification problem, and we have been paying frontier prices to do it one page at a time. what you are watching: left column is Jev, right is Opus, same queue, same rubric. the run stops the moment Jev finishes so Opus stops burning tokens. coming soon to Distribb + connector + gpt plugin

Jev is WILD for SEO audit 🤯 in 45.1 seconds it read all 586 pages on my site and rebuilt the internal link map. 584 links placed, 139 pages it refused to link because nothing honestly fit. total cost $0.21. Claude Opus 5, same 586 pages, same clock, got through 21 of them and spent $1.43. per page that is ~190x cheaper. the full Opus pass would have run $43. internal linking is the perfect Jev job. it is not writing, it is 8,790 yes/no calls: does this page have a real reason to link to that one, and is there anchor text already sitting in the copy. that is a classification problem, and we have been paying frontier prices to do it one page at a time. what you are watching: left column is Jev, right is Opus, same queue, same rubric. the run stops the moment Jev finishes so Opus stops burning tokens. coming soon to Distribb + connector + gpt plugin

borja

842,738 views • 16 days ago

this is f*cking gold 20 GitHub repos with 500K+ combined stars that will level up your JEV workflow AGENTS > jev-ultrafast: Jev picks every click and DOM target, a small LLM only types > hermes-jev-skills: routing, memory, compaction and skill picks in one pack > typesafe-computer-use: OCR reads your Mac screen, Jev picks the next click MEMORY > fast-jev-compaction: scores every tool call keep, truncate or drop instead of summarizing > jevmem: project memory for Claude Code, Cursor and Codex, updated every turn > jev-second-brain: your Obsidian vault, Jev judges which notes duplicate, revise or contradict SAFETY > jev-guard: a gate before every tool call, Jev scores the risk, you set allow, ask or deny TOOLS > skills: the official TypeSafe skill for Claude Code and Codex > system-one-adapter-python: dry-run your questions on an ordinary LLM before you burn a Jev key > jev-mcp: claim checks, screening and ranking as MCP tools > typesafe-mcp: plug Jev into any MCP client > json-render: Vercel's generative UI, where Jev picks the components OPEN MODELS > SemIf-OpenJev: semantic ifs from frozen open models kev: Jev-like models on Qwen that run on your MacBook > laya-mlx: the Laya decision engine on Apple silicon > clm: an open System One model with Choice, Noul and Score > jevlike: train your own Jev-like model TRADING > jev-trader: one buy or sell decision per Monad block START HERE > awesome-jev: the biggest map of everything built on Jev > awesome-jev-by-typesafe: use cases, patterns and starter code bookmark it before your next build

this is f*cking gold 20 GitHub repos with 500K+ combined stars that will level up your JEV workflow AGENTS > jev-ultrafast: Jev picks every click and DOM target, a small LLM only types > hermes-jev-skills: routing, memory, compaction and skill picks in one pack > typesafe-computer-use: OCR reads your Mac screen, Jev picks the next click MEMORY > fast-jev-compaction: scores every tool call keep, truncate or drop instead of summarizing > jevmem: project memory for Claude Code, Cursor and Codex, updated every turn > jev-second-brain: your Obsidian vault, Jev judges which notes duplicate, revise or contradict SAFETY > jev-guard: a gate before every tool call, Jev scores the risk, you set allow, ask or deny TOOLS > skills: the official TypeSafe skill for Claude Code and Codex > system-one-adapter-python: dry-run your questions on an ordinary LLM before you burn a Jev key > jev-mcp: claim checks, screening and ranking as MCP tools > typesafe-mcp: plug Jev into any MCP client > json-render: Vercel's generative UI, where Jev picks the components OPEN MODELS > SemIf-OpenJev: semantic ifs from frozen open models kev: Jev-like models on Qwen that run on your MacBook > laya-mlx: the Laya decision engine on Apple silicon > clm: an open System One model with Choice, Noul and Score > jevlike: train your own Jev-like model TRADING > jev-trader: one buy or sell decision per Monad block START HERE > awesome-jev: the biggest map of everything built on Jev > awesome-jev-by-typesafe: use cases, patterns and starter code bookmark it before your next build

NO1ennn

18,445 views • 6 days ago

Official Anthropic tip for Claude Code: stop burning Opus 5.5 on work Sonnet 5.5 can do, while Fable 5.1 sits idle hand the grunt work to Sonnet 5.5 subagents and put Fable 5.1 on call run /advisor fable Opus 5.5 plans and merges Sonnet 5.5 subagents read, edit and run the tests Fable 5.1 reads the full session and only speaks up at three points: → before a plan: is this the right approach? → when the same error comes back: am I digging in the wrong place? → before "done": what did I miss? Sonnet 5.5 builds. Fable 5.1 reviews. Opus 5.5 ships Jev engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to Jev in under half a second, and the big models only see the ones that split - the full tree > Opus 5.5 on high runs the main session > explorer reads the code on Sonnet 5.5 > worker edits and runs tests on Sonnet 5.5 > researcher pulls the docs on Sonnet 5.5 > all three on medium > Fable 5.1 on call for main and every subagent paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Check ~/.claude/agents and .claude/agents for subagents that already fit explorer, worker and researcher. > Draft new ones only for missing roles > Give each model: sonnet, effort: medium > Skip any that pin a different model and list them 2. Set the main session to high via effortLevel in ~/.claude/settings.json, and set advisorModel to fable 3. Find anything that keeps the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY) plus CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report them, change nothing 4. Add one rule to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done Show me every change as a diff first. No edits until I say go." ↳

Official Anthropic tip for Claude Code: stop burning Opus 5.5 on work Sonnet 5.5 can do, while Fable 5.1 sits idle hand the grunt work to Sonnet 5.5 subagents and put Fable 5.1 on call run /advisor fable Opus 5.5 plans and merges Sonnet 5.5 subagents read, edit and run the tests Fable 5.1 reads the full session and only speaks up at three points: → before a plan: is this the right approach? → when the same error comes back: am I digging in the wrong place? → before "done": what did I miss? Sonnet 5.5 builds. Fable 5.1 reviews. Opus 5.5 ships Jev engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to Jev in under half a second, and the big models only see the ones that split - the full tree > Opus 5.5 on high runs the main session > explorer reads the code on Sonnet 5.5 > worker edits and runs tests on Sonnet 5.5 > researcher pulls the docs on Sonnet 5.5 > all three on medium > Fable 5.1 on call for main and every subagent paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Check ~/.claude/agents and .claude/agents for subagents that already fit explorer, worker and researcher. > Draft new ones only for missing roles > Give each model: sonnet, effort: medium > Skip any that pin a different model and list them 2. Set the main session to high via effortLevel in ~/.claude/settings.json, and set advisorModel to fable 3. Find anything that keeps the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY) plus CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report them, change nothing 4. Add one rule to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done Show me every change as a diff first. No edits until I say go." ↳

delost

42,409 views • 2 days ago

CLAUDE CODE + GROK + JEV - THE FILE WHERE THREE HEADS CLOSE A TICKET IN 9 MINUTES FOR $1.74 a month of this costs $208.80, the same 120 merges by hand are 300 hours and $28,500 ticket → plan → patch → tests → review → merge Claude Code on Opus 5.5 writes the patch, Grok reads it back and argues, Jev holds the gate and merges only on green tests three heads, and not one of them is allowed to push code to prod on its own 38 files read, 3 touched, +412 lines, 48 tests, and the first four failed, so the patch went back two minutes twenty later it was 48 of 48, and only then did Jev open the gate out of 120 patches Claude Code and Grok signed off on 78 straight away and had a fight about the other 22 those 22 arguments are the product, because a reviewer that never objects is just decoration the meter clocked $208.80 for the month, and to catch the human bill it would have to keep running for another 136 months and here is the brutal part of this file: 6 of the 94 merged tickets came back with bugs every one of them sat in the part of the code the test suite has never read, because coverage there is 61% two models in the same blind spot is not two opinions, it is one mistake signed twice save this and paste it into Claude Code - let it run your ticket through these three heads ↓

CLAUDE CODE + GROK + JEV - THE FILE WHERE THREE HEADS CLOSE A TICKET IN 9 MINUTES FOR $1.74 a month of this costs $208.80, the same 120 merges by hand are 300 hours and $28,500 ticket → plan → patch → tests → review → merge Claude Code on Opus 5.5 writes the patch, Grok reads it back and argues, Jev holds the gate and merges only on green tests three heads, and not one of them is allowed to push code to prod on its own 38 files read, 3 touched, +412 lines, 48 tests, and the first four failed, so the patch went back two minutes twenty later it was 48 of 48, and only then did Jev open the gate out of 120 patches Claude Code and Grok signed off on 78 straight away and had a fight about the other 22 those 22 arguments are the product, because a reviewer that never objects is just decoration the meter clocked $208.80 for the month, and to catch the human bill it would have to keep running for another 136 months and here is the brutal part of this file: 6 of the 94 merged tickets came back with bugs every one of them sat in the part of the code the test suite has never read, because coverage there is 61% two models in the same blind spot is not two opinions, it is one mistake signed twice save this and paste it into Claude Code - let it run your ticket through these three heads ↓

Sprytix

11,673 views • 3 days ago

JEV + Opus 5.5 is insane for live design... I built a live site redesigner with JEV + Opus 5.5 Paste any link → press Start → scroll, and Jev + Opus 5.5 rebuild every section of the site in front of you Full production ship in 20 seconds: 1. IntersectionObserver fires when a section is 30%+ in the viewport 2. Jev returns one typed decision in ~0.1s: { layout, copy, drop, type, palette, p } 3. Opus 5.5 writes the component (TSX) + a CSS patch for the chosen style 4. The new section wipes in with clip-path, the old one blurs out 5. Next section enters the queue, one at a time, no race conditions Output: 8 sections of a 2015 hosting site rebuilt in ~20s, streamed line by line in the terminal 3 styles, one renderer: orthographic globe + lambert shading → ASCII / 2-color halftone / ink stipple Scroll yourself and it redesigns whatever you land on Jev decides fast, Opus designs it

JEV + Opus 5.5 is insane for live design... I built a live site redesigner with JEV + Opus 5.5 Paste any link → press Start → scroll, and Jev + Opus 5.5 rebuild every section of the site in front of you Full production ship in 20 seconds: 1. IntersectionObserver fires when a section is 30%+ in the viewport 2. Jev returns one typed decision in ~0.1s: { layout, copy, drop, type, palette, p } 3. Opus 5.5 writes the component (TSX) + a CSS patch for the chosen style 4. The new section wipes in with clip-path, the old one blurs out 5. Next section enters the queue, one at a time, no race conditions Output: 8 sections of a 2015 hosting site rebuilt in ~20s, streamed line by line in the terminal 3 styles, one renderer: orthographic globe + lambert shading → ASCII / 2-color halftone / ink stipple Scroll yourself and it redesigns whatever you land on Jev decides fast, Opus designs it

Movez

105,501 views • 10 days ago

ANTHROPIC LEAKED A FILE WHERE 5 AGENTS WITH JEV BUILD A $1.2M A YEAR SYSTEM IN 30 MINUTES you pay $3.70 and walk away with an asset that can do $1.2M a year repo → data model → API → UI → evals no layer starts until the one under it is closed, and that edge is what turns five scripts into a system the operator on Haiku 4.5 brings up the repo and CI, the architect on Opus 5 lays down the data model and migrations two builders on Sonnet 5 run API and UI in parallel, and the reviewer on Opus 5.5 can keep finished code out of prod the evals were sitting in the file before the first line of code existed at minute zero there was not a single file, by the end it is a working product with payments and tests five agents cover in half an hour what a human team bills for a quarter JEV hands one line between layers instead of the whole history, so the next agent never re-reads the project and the run costs $3.70 instead of $370 the build takes 30 minutes, the first customers show up weeks later save this and paste it into Claude Code - let it assemble those 5 layers for you ↓

ANTHROPIC LEAKED A FILE WHERE 5 AGENTS WITH JEV BUILD A $1.2M A YEAR SYSTEM IN 30 MINUTES you pay $3.70 and walk away with an asset that can do $1.2M a year repo → data model → API → UI → evals no layer starts until the one under it is closed, and that edge is what turns five scripts into a system the operator on Haiku 4.5 brings up the repo and CI, the architect on Opus 5 lays down the data model and migrations two builders on Sonnet 5 run API and UI in parallel, and the reviewer on Opus 5.5 can keep finished code out of prod the evals were sitting in the file before the first line of code existed at minute zero there was not a single file, by the end it is a working product with payments and tests five agents cover in half an hour what a human team bills for a quarter JEV hands one line between layers instead of the whole history, so the next agent never re-reads the project and the run costs $3.70 instead of $370 the build takes 30 minutes, the first customers show up weeks later save this and paste it into Claude Code - let it assemble those 5 layers for you ↓

Sprytix

14,208 views • 9 days ago

Do you understand what just got open sourced? 5,800+ quant trading strategies for FREE along with its CODEBASE i gave these trading strategies to opus 5.5 + jev and it built me a PROFITABLE 24/7 trading agent here is how to use the repo and build AI trading bot: 1. clone the vault and get 5,806 trading strategies (spot, perps, grid, stat arb and market making) 2. open any strategy file, the math, the parameters and the source are already inside 3. point AgenKit at that file inside Claude Code with model as opus 5.5, one command and it reads the spec as ground truth 4. it will run a full engineering team and ships a production bot with risk controls 5. Jev is the live brain, it answers buy sell or hold in 81 milliseconds, calibrated, no hallucination 6. your engine sizes the trade from that confidence and fires it before the next block 7. a hard risk layer holds every limit, nothing goes live until you approve it 8. every night Opus 5.5 reviews the fills and ships a better version, so the agent improves while you sleep one model THINKS, the other REACTS and a strategy that sat locked in a vault now trades itself 24/7 the COMPLETE codebase and the EXACT Opus 5.5 + Jev trading system which I am running is in the article below:

Do you understand what just got open sourced? 5,800+ quant trading strategies for FREE along with its CODEBASE i gave these trading strategies to opus 5.5 + jev and it built me a PROFITABLE 24/7 trading agent here is how to use the repo and build AI trading bot: 1. clone the vault and get 5,806 trading strategies (spot, perps, grid, stat arb and market making) 2. open any strategy file, the math, the parameters and the source are already inside 3. point AgenKit at that file inside Claude Code with model as opus 5.5, one command and it reads the spec as ground truth 4. it will run a full engineering team and ships a production bot with risk controls 5. Jev is the live brain, it answers buy sell or hold in 81 milliseconds, calibrated, no hallucination 6. your engine sizes the trade from that confidence and fires it before the next block 7. a hard risk layer holds every limit, nothing goes live until you approve it 8. every night Opus 5.5 reviews the fills and ships a better version, so the agent improves while you sleep one model THINKS, the other REACTS and a strategy that sat locked in a vault now trades itself 24/7 the COMPLETE codebase and the EXACT Opus 5.5 + Jev trading system which I am running is in the article below:

Roan

93,835 views • 7 days ago

Claude Code tip: once Opus 5.5 is your main model, stop leaving Fable 5.1 sitting idle put it on call with /advisor run /advisor fable Opus 5.5 keeps writing the code Fable 5.1 reads the full session, every tool call included, and only speaks up at three points: → before a plan: is this the right approach? → when the same error comes back: am I digging in the wrong place? → before "done": what did I miss? Fable 5.1 reviews. Opus 5.5 ships Jev engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to Jev in under half a second, and the big model only sees the ones that split - the full tree > Opus 5.5 on high runs the main session > explorer reads the code > worker edits and runs tests > researcher pulls the docs > all three on medium > Fable 5.1 on call as the advisor paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Check ~/.claude/agents and .claude/agents for subagents that already fit explorer, worker and researcher. > Draft new ones only for missing roles > Give each model: opus, effort: medium > Skip any that pin a different model and list them 2. Set the main session to high via effortLevel in ~/.claude/settings.json, and set advisorModel to fable 3. Find anything that keeps the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, any variable that stops feature-flag fetching) plus CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report them, change nothing 4. Add one rule to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done Show me every change as a diff first. No edits until I say go." ↳

Claude Code tip: once Opus 5.5 is your main model, stop leaving Fable 5.1 sitting idle put it on call with /advisor run /advisor fable Opus 5.5 keeps writing the code Fable 5.1 reads the full session, every tool call included, and only speaks up at three points: → before a plan: is this the right approach? → when the same error comes back: am I digging in the wrong place? → before "done": what did I miss? Fable 5.1 reviews. Opus 5.5 ships Jev engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to Jev in under half a second, and the big model only sees the ones that split - the full tree > Opus 5.5 on high runs the main session > explorer reads the code > worker edits and runs tests > researcher pulls the docs > all three on medium > Fable 5.1 on call as the advisor paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Check ~/.claude/agents and .claude/agents for subagents that already fit explorer, worker and researcher. > Draft new ones only for missing roles > Give each model: opus, effort: medium > Skip any that pin a different model and list them 2. Set the main session to high via effortLevel in ~/.claude/settings.json, and set advisorModel to fable 3. Find anything that keeps the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, any variable that stops feature-flag fetching) plus CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report them, change nothing 4. Add one rule to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done Show me every change as a diff first. No edits until I say go." ↳

delost

693,243 views • 6 days ago

Jev has been exploding in popularity recently. If you already have access to the Jev API but aren't sure how to start experimenting with it, just copy this checklist: 1. jev-ultrafast Browser Use's fastest agent. Jev decides the next action and which element to click, and a language model is only called when text has to be typed. 2. typesafe-mario Jev plays Super Mario Bros. from structured emulator state, choosing every action from features pulled out of the game. 3. jev-plays-pokemon Reads Pokémon Red's game state as text, answers typed questions each turn, and lets plain code turn the answers into moves. 4. jev-drone A camera-only autonomous drone in MuJoCo with a Jev judgment model sitting in the control loop at 2.5 Hz. 5. robo-harness A real SO-101 robot arm workbench where Jev picks bounded joint steps from typed candidate actions under a spend budget. 6. fast-jev-compaction Claude Code plugin that replaces the compaction summary with Jev decisions, scoring every tool call for whether it is still needed. 7. jev-claude Routes Claude Code's own judgment calls through Jev: typed choices with probabilities at plan approval, on questions, and before risky commands. 8. is-malicious Supply-chain check before you run anything: Jev Noul checks over source and build files, returning the implicated files and lines. 9. sqlite-jev Jev inside SQL. Noul, Choice and Score judgments exposed as SQLite functions, with confidence on every row. 10. jevinci Paints images by having Jev predict every pixel's colour in parallel, with confidence deciding how wide each stroke is drawn. Copy these complete Jev blueprints - then read full Jev setup below ↓ ↓

Jev has been exploding in popularity recently. If you already have access to the Jev API but aren't sure how to start experimenting with it, just copy this checklist: 1. jev-ultrafast Browser Use's fastest agent. Jev decides the next action and which element to click, and a language model is only called when text has to be typed. 2. typesafe-mario Jev plays Super Mario Bros. from structured emulator state, choosing every action from features pulled out of the game. 3. jev-plays-pokemon Reads Pokémon Red's game state as text, answers typed questions each turn, and lets plain code turn the answers into moves. 4. jev-drone A camera-only autonomous drone in MuJoCo with a Jev judgment model sitting in the control loop at 2.5 Hz. 5. robo-harness A real SO-101 robot arm workbench where Jev picks bounded joint steps from typed candidate actions under a spend budget. 6. fast-jev-compaction Claude Code plugin that replaces the compaction summary with Jev decisions, scoring every tool call for whether it is still needed. 7. jev-claude Routes Claude Code's own judgment calls through Jev: typed choices with probabilities at plan approval, on questions, and before risky commands. 8. is-malicious Supply-chain check before you run anything: Jev Noul checks over source and build files, returning the implicated files and lines. 9. sqlite-jev Jev inside SQL. Noul, Choice and Score judgments exposed as SQLite functions, with confidence on every row. 10. jevinci Paints images by having Jev predict every pixel's colour in parallel, with confidence deciding how wide each stroke is drawn. Copy these complete Jev blueprints - then read full Jev setup below ↓ ↓

Hanako

29,894 views • 10 days ago

Another insane Jev use case! Jev is making it dramatically cheaper to evaluate what actually happened inside an agent run. And finally, someone open-sourced a self-improving memory layer that can put that signal to work across agent harnesses: - Claude Code - Codex - Cursor - OpenCode, and 20+ more Beacon by Asymptote Labs continuously captures your agent history across harnesses and uses Jev to identify which runs are actually worth learning from. It then turns the highest-signal workflows, corrections, and debugging patterns into reusable skills. GitHub repo: (don’t forget to star it ⭐ ) Beacon preserves the complete session history. But preserving a run and learning from it are two different things. Most coding-agent sessions contain routine exploration, failed commands, and fixes that only apply to one task. The trace can remain available for inspection without turning every detail into guidance for future agents. Jev scores each run for evidence, reuse potential, and human correction signals. An application policy then decides whether to promote, review, or discard it. The recording shows this in action. Claude receives a coding task, modifies the implementation, and runs the tests. I then provide an edge-case correction, so Claude updates the code and adds regression coverage. Beacon automatically captures the complete session. Jev evaluates whether the correction contains a reusable engineering lesson. Once approved, that lesson becomes available to other coding agents working on the project. Since it works across harnesses: - Claude Code sessions can teach Codex. - Cursor debugging can improve OpenCode. So a problem solved by one agent should not need to be learned from scratch by another. If you want to dive deeper into Jev, I also wrote a hands-on guide to building this Jev-style decision path with open models, entirely locally. Read it below.

Another insane Jev use case! Jev is making it dramatically cheaper to evaluate what actually happened inside an agent run. And finally, someone open-sourced a self-improving memory layer that can put that signal to work across agent harnesses: - Claude Code - Codex - Cursor - OpenCode, and 20+ more Beacon by Asymptote Labs continuously captures your agent history across harnesses and uses Jev to identify which runs are actually worth learning from. It then turns the highest-signal workflows, corrections, and debugging patterns into reusable skills. GitHub repo: (don’t forget to star it ⭐ ) Beacon preserves the complete session history. But preserving a run and learning from it are two different things. Most coding-agent sessions contain routine exploration, failed commands, and fixes that only apply to one task. The trace can remain available for inspection without turning every detail into guidance for future agents. Jev scores each run for evidence, reuse potential, and human correction signals. An application policy then decides whether to promote, review, or discard it. The recording shows this in action. Claude receives a coding task, modifies the implementation, and runs the tests. I then provide an edge-case correction, so Claude updates the code and adds regression coverage. Beacon automatically captures the complete session. Jev evaluates whether the correction contains a reusable engineering lesson. Once approved, that lesson becomes available to other coding agents working on the project. Since it works across harnesses: - Claude Code sessions can teach Codex. - Cursor debugging can improve OpenCode. So a problem solved by one agent should not need to be learned from scratch by another. If you want to dive deeper into Jev, I also wrote a hands-on guide to building this Jev-style decision path with open models, entirely locally. Read it below.

Avi Chawla

291,153 views • 13 days ago

OPUS 5.5 + SONNET 5.5 + JEV + DOTS on one spider, and 90% of your work is gone... one spider reads 5,152 items across 6 sources that you never open: 2,140 emails, 1,204 CRM records, 860 slack messages nothing waits for you to write a prompt, because Dots is always on and owns the job 24/7 every item gets a decision from Jev in 81 ms, so all 5,152 take under 7 minutes: urgent or not, how risky, and 1 of 3 routes the routine work goes to Sonnet 5.5, 12 drafts in this run, 12 marked done, 0 written by you the whole time Opus 5.5 sleeps and wakes up for 1 hard case out of 5,152. the other 5,151 never wake it your share drops from 100% to 10%, the other 90% of your work is gone ↓

OPUS 5.5 + SONNET 5.5 + JEV + DOTS on one spider, and 90% of your work is gone... one spider reads 5,152 items across 6 sources that you never open: 2,140 emails, 1,204 CRM records, 860 slack messages nothing waits for you to write a prompt, because Dots is always on and owns the job 24/7 every item gets a decision from Jev in 81 ms, so all 5,152 take under 7 minutes: urgent or not, how risky, and 1 of 3 routes the routine work goes to Sonnet 5.5, 12 drafts in this run, 12 marked done, 0 written by you the whole time Opus 5.5 sleeps and wakes up for 1 hard case out of 5,152. the other 5,151 never wake it your share drops from 100% to 10%, the other 90% of your work is gone ↓

Noisy

36,018 views • 1 day ago