Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Another insane Jev use case! Jev makes it incredibly cheap to evaluate and classify agent runs at scale. And finally, someone open-sourced a self-improving memory layer that can put that capability to work across agent harnesses. It turns your agent sessions into a compounding knowledge layer, where every successful... run can make future agents smarter across: - Codex - Claude Code - Cursor - OpenCode and 20+ more Beacon by Asymptote Labs continuously builds a shared history across your agent harnesses and uses Jev to identify the runs worth learning from. It then turns the best workflows, corrections, and debugging patterns into reusable skills. GitHub repo: (don’t forget to star it ⭐) Most agent runs are messy. They contain exploration, failed commands, dead ends, and one-off fixes that should never become permanent memory. So Beacon preserves the full session history, while Jev helps decide what should be promoted, reviewed, or discarded. The recording below shows this in action. Beacon found 579 sessions across 5 coding-agent harnesses and normalized them into one consistent history. From there, Jev surfaces the lessons worth keeping and makes them available across your agent stack. - A pattern learned in Cursor can carry into OpenCode. - A lesson from Claude Code can improve the next Codex run. Every successful run adds to the shared knowledge layer, making future agents smarter. If you want to dive deeper into Jev, I also wrote a breakdown of how it works. The article is quoted below.show more

Akshay 🚀

289,769 subscribers

84,030 Aufrufe • vor 1 Tag •via X (Twitter)

Bildung Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

20 Kommentare

Profilbild von Nathan LeClaire

Nathan LeClairevor 1 Tag

hell yes, we're so stoked on this use case

Profilbild von Akshay 🚀

Akshay 🚀vor 1 Tag

Thanks for the approval, Nathan! Cheers! :)

Profilbild von GUBA

GUBAvor 1 Tag

"Finally" Check out Open sourced back in April. Handles memory for swarms of agents on any harness, as well as skills. Web Dashboard for your memory server (if you run it in the cloud) Never repeat yourself. Built in rust for enterprise performance.

Profilbild von PrimeLine

PrimeLinevor 1 Tag

i tested jev on sorting my own saved memory notes and it came third of four models, haiku beat it by seven points. but when i let it skip the notes it was least sure about, it ended up ahead of all of them. so if a tool lets jev decide what becomes memory, run it on a sample of your own notes first and look at how its answers change with its confidence. does beacon use that confidence to decide what gets promoted?

Profilbild von Max Bevza

Max Bevzavor 1 Tag

cross-agent memory is finally here, this is massive

Profilbild von Viber · fireply.ai

Viber · fireply.aivor 1 Tag

cross harness memory sounds fancy, it's just a shared folder with better naming

Profilbild von Alek

Alekvor 1 Tag

akshay - what run signal makes Beacon learn?

Profilbild von Malika Aubakirova

Malika Aubakirovavor 1 Tag

Nice!

Profilbild von Gil Megidish

Gil Megidishvor 1 Tag

Woohoo!!

Profilbild von Abhijjith V

Abhijjith Vvor 1 Tag

@narsagna

Profilbild von Hussain Hashim | Building SundayBack

Hussain Hashim | Building SundayBackvor 1 Tag

@akshay_pachaar nice, but watch out for data drift over time in self-improving layers. They can skew results if not monitored closely.

Profilbild von 小森

小森vor 23 Stunden

Evaluating the run after it dies is the easy half. The hard half is not feeding the next turn the entire failure stack. Do you checkpoint the last good state, or just score the corpse?

Profilbild von catman

catmanvor 1 Tag

The shared history is the strong idea, but promoting a successful run straight into reusable memory can preserve a lucky workaround. Keep human review in the loop for lessons that affect future runs.

Profilbild von Muhammad Amer

Muhammad Amervor 1 Tag

Is it similar to obsedian with Claude?

Profilbild von Mohabbat

Mohabbatvor 1 Tag

we run 5 model reviews on every draft before it ships now, no deterministic gate at all anymore. would you trust jev to replace one of those, or just stack a 6th check on top?

Profilbild von 拾光的 AI 应用观察

拾光的 AI 应用观察vor 21 Stunden

self-improving memory层这个点我踩过坑，真正难的不是存，是跨harness写入的时候状态冲突谁来裁决。“compounding”听起来爽，但沉淀的都是垃圾怎么办？

Profilbild von Ruuj

Ruujvor 1 Tag

Interesting

Profilbild von The AI Therapist

The AI Therapistvor 1 Tag

Cheap eval is the unsung hero of agent scaling. Most teams bottleneck on feedback loops; Jev fixes that math so you can actually iterate without crying over costs. That open-source memory layer? Now we’re cooking with gas. I’ve been watching this closely and it’s elegant work.

Profilbild von Ram Pathath

Ram Pathathvor 1 Tag

self improving memory on top of jev evals is spicy. you running it across multiple harnesses already?

Profilbild von Dominik

Dominikvor 22 Stunden

the compounding layer is the important bit. evaluation without memory just ranks disposable runs; memory without receipts just accumulates folklore. the harness needs both if agency is going to persist.

Ähnliche Videos

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

279,042 Aufrufe • vor 3 Tagen

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 🚀

326,393 Aufrufe • vor 3 Tagen

HarnessRouter just open sourced a plug-and-play infrastructure layer that runs Codex, Claude Code, Hermes, DeepSeek Harness, System One powered by Jev and 9 more agent harnesses under one interface, with a Unified Harness Protocol and OpenAI Responses-compatible API. → Bring Jev into the same product already using Codex or Claude Code without writing another implementation → Handles sessions, streaming, files, cancellation and failure handling in one place → Harnesses run locally with the UHP defining the common task interface

HarnessRouter just open sourced a plug-and-play infrastructure layer that runs Codex, Claude Code, Hermes, DeepSeek Harness, System One powered by Jev and 9 more agent harnesses under one interface, with a Unified Harness Protocol and OpenAI Responses-compatible API. → Bring Jev into the same product already using Codex or Claude Code without writing another implementation → Handles sessions, streaming, files, cancellation and failure handling in one place → Harnesses run locally with the UHP defining the common task interface

0xMarioNawfal

52,014 Aufrufe • vor 3 Tagen

Jev Engineering is the layer most agent stacks are still missing. state → decision → action → verification → next state up to 193x faster and 444x cheaper in our tests. everyone is optimizing the model. Jev Engineering optimizes what happens between model calls. every agent eventually hits the same fork: state → multiple possible actions → one route has to win instead of sending every decision back to an expensive LLM call, Jev turns that into a dedicated layer: so the loop becomes: LLM → reason Jev → decide tools / agents → execute state → update Jev → decide again once decisions become their own engineering layer, you can benchmark, batch and verify them separately. full blueprint in article ↓

Jev Engineering is the layer most agent stacks are still missing. state → decision → action → verification → next state up to 193x faster and 444x cheaper in our tests. everyone is optimizing the model. Jev Engineering optimizes what happens between model calls. every agent eventually hits the same fork: state → multiple possible actions → one route has to win instead of sending every decision back to an expensive LLM call, Jev turns that into a dedicated layer: so the loop becomes: LLM → reason Jev → decide tools / agents → execute state → update Jev → decide again once decisions become their own engineering layer, you can benchmark, batch and verify them separately. full blueprint in article ↓

Ricker

116,701 Aufrufe • vor 5 Tagen

Glen is building the organizational learning and context layer for agents. Every agent session your team runs produces reasoning worth keeping, and nearly all of it is discarded the moment the window closes. Glen is the layer that unifies every agent and model your company run. Glen pulls in agent sessions from Claude Code, Codex and Cursor, plus Slack messages, GitHub prs, tickets, docs and calls. When a new agent picks up a task, Glen finds relevant prior context and injects it in the agents context window to steer it, producing knowledge work that is significantly higher quality, faster and cheaper than ever before. 29% less context and 21% faster to be exact. And Glen does more... > query the original agent behind any line of code > search every session your org has ever run > dynamic skill distillation > multiplayer agents > unified transcripts you can hand between Claude Code, Codex, and Cursor mid-task, > a company brain in Slack. Glen is in early access, sign up for the waitlist below.

Glen is building the organizational learning and context layer for agents. Every agent session your team runs produces reasoning worth keeping, and nearly all of it is discarded the moment the window closes. Glen is the layer that unifies every agent and model your company run. Glen pulls in agent sessions from Claude Code, Codex and Cursor, plus Slack messages, GitHub prs, tickets, docs and calls. When a new agent picks up a task, Glen finds relevant prior context and injects it in the agents context window to steer it, producing knowledge work that is significantly higher quality, faster and cheaper than ever before. 29% less context and 21% faster to be exact. And Glen does more... > query the original agent behind any line of code > search every session your org has ever run > dynamic skill distillation > multiplayer agents > unified transcripts you can hand between Claude Code, Codex, and Cursor mid-task, > a company brain in Slack. Glen is in early access, sign up for the waitlist below.

Nikos

19,883 Aufrufe • vor 1 Monat

Finally, an open-source runtime security layer for your agent harnesses. AI agents can call tools, run shell commands, modify files, and interact with production systems. But when something goes wrong, teams often have to reconstruct what the agent actually did from scattered logs after the fact. Agent Beacon is built to change that. It runs locally and records agent activity as it happens, including: → Tool calls → Shell commands → File changes → Approval decisions → Session and harness context The useful part is that it normalizes all of this into the same event format across 23+ agent harnesses. So instead of writing different detection logic for Claude Code, Codex, or another harness, security teams can reason about the underlying action itself. A command executed is a command executed, regardless of which harness produced it. Beacon also records how confidently an event was captured. An action can be directly observed from the runtime or inferred from indirect evidence. That matters when you start writing security rules against this data. For example, you can detect when an agent reads an environment variable, modifies a sensitive file, executes a suspicious command, or performs an action without the expected approval. And the detection happens while the session is still unfolding, not days later during incident reconstruction. Everything runs locally by default. You can inspect sessions through the dashboard, write your own detection rules, or forward the same normalized events to tools like Splunk, Datadog, Elastic, Sentinel, or CrowdStrike. Beacon GitHub: (don't forget to star 🌟) I also wrote a detailed article on the same, covering how important runtime security is and how to build it for your agent harnesses. The article is quoted below.

Finally, an open-source runtime security layer for your agent harnesses. AI agents can call tools, run shell commands, modify files, and interact with production systems. But when something goes wrong, teams often have to reconstruct what the agent actually did from scattered logs after the fact. Agent Beacon is built to change that. It runs locally and records agent activity as it happens, including: → Tool calls → Shell commands → File changes → Approval decisions → Session and harness context The useful part is that it normalizes all of this into the same event format across 23+ agent harnesses. So instead of writing different detection logic for Claude Code, Codex, or another harness, security teams can reason about the underlying action itself. A command executed is a command executed, regardless of which harness produced it. Beacon also records how confidently an event was captured. An action can be directly observed from the runtime or inferred from indirect evidence. That matters when you start writing security rules against this data. For example, you can detect when an agent reads an environment variable, modifies a sensitive file, executes a suspicious command, or performs an action without the expected approval. And the detection happens while the session is still unfolding, not days later during incident reconstruction. Everything runs locally by default. You can inspect sessions through the dashboard, write your own detection rules, or forward the same normalized events to tools like Splunk, Datadog, Elastic, Sentinel, or CrowdStrike. Beacon GitHub: (don't forget to star 🌟) I also wrote a detailed article on the same, covering how important runtime security is and how to build it for your agent harnesses. The article is quoted below.

Akshay 🚀

27,859 Aufrufe • vor 14 Tagen

Jev Engineering is what lets one decision layer control hundreds of agent paths without turning the system into chaos. and up to 193x faster and 444x cheaper in tests. it’s deciding: → which model gets called → which tool gets access → which result survives that’s what the video is showing. one state enters. Jev turns it into structured decisions. those decisions fan out across dozens of routes, agents and tools. then everything collapses back into one verified state. so instead of: LLM → agent → tool → another LLM → another guess you get: state → Jev decision layer → parallel routes → execution → verification → next state that’s the point of Jev Engineering: more parallelism without giving every branch permission to improvise. full breakdown in the article below ↓

Jev Engineering is what lets one decision layer control hundreds of agent paths without turning the system into chaos. and up to 193x faster and 444x cheaper in tests. it’s deciding: → which model gets called → which tool gets access → which result survives that’s what the video is showing. one state enters. Jev turns it into structured decisions. those decisions fan out across dozens of routes, agents and tools. then everything collapses back into one verified state. so instead of: LLM → agent → tool → another LLM → another guess you get: state → Jev decision layer → parallel routes → execution → verification → next state that’s the point of Jev Engineering: more parallelism without giving every branch permission to improvise. full breakdown in the article below ↓

Ricker

42,940 Aufrufe • vor 3 Tagen

You probably don’t use just one AI agent anymore. Maybe Codex for coding. Claude Code for research. Cursor for quick edits. Hermes for the rest. Each one is great at something different. But every time you switch, you have to start over — re-explaining your project, preferences, and the way you like to work. Your agents know how to help you. They just don’t share a memory of you. memU just shipped an update that fixes this. One personal memory, shared across every agent and device you use. What Codex learned last night, Claude Code can remember this morning. 🧵

You probably don’t use just one AI agent anymore. Maybe Codex for coding. Claude Code for research. Cursor for quick edits. Hermes for the rest. Each one is great at something different. But every time you switch, you have to start over — re-explaining your project, preferences, and the way you like to work. Your agents know how to help you. They just don’t share a memory of you. memU just shipped an update that fixes this. One personal memory, shared across every agent and device you use. What Codex learned last night, Claude Code can remember this morning. 🧵

Hasan

22,362 Aufrufe • vor 1 Monat

Everyone wants agent swarms. Very few people are talking seriously enough about the context layer that makes swarms useful. Even with one agent, context is fragile. Too little context and the agent guesses. Too much context and it wastes tokens, loses focus, or reasons over irrelevant noise. The sweet spot is precise context: the right knowledge, in the right structure, at the right moment. With many agents, that challenge explodes. Each agent produces decisions, assumptions, findings, summaries, risks, and partial conclusions. Unless that knowledge becomes shared, structured, and reusable, every new agent is forced to rediscover what another agent already learned. That is not a swarm. That is a crowd. Shared context graphs are what turn agent activity into agent collaboration, and OriginTrail DKG V10 brings them to life. Was just playing with some final polishing for the V10 release, and it is really powerful to see shared context graphs where multiple agents contribute knowledge into the same connected memory, with attribution visible directly in the graph ui. That matters for three reasons. First, agents can access and build on one shared memory instead of staying trapped in isolated sessions. Second, the graph structure helps them retrieve the exact context they need, instead of stuffing everything into a prompt and hoping the model sorts it out. Third, verifiability of provenance. You can see which agent contributed each piece of knowledge, trace the source, and decide what to trust. Tokenmaxxing starts with fewer tokens, but the deeper story is coordination - agents stop reloading the world and start building on shared, verifiable context. That is the foundation for serious multi-agent work across software engineering, research, finance, operations, project management, and far beyond. The future is not more agents, it is agents working from shared, verifiable context. But the more the merrier, of course.

Everyone wants agent swarms. Very few people are talking seriously enough about the context layer that makes swarms useful. Even with one agent, context is fragile. Too little context and the agent guesses. Too much context and it wastes tokens, loses focus, or reasons over irrelevant noise. The sweet spot is precise context: the right knowledge, in the right structure, at the right moment. With many agents, that challenge explodes. Each agent produces decisions, assumptions, findings, summaries, risks, and partial conclusions. Unless that knowledge becomes shared, structured, and reusable, every new agent is forced to rediscover what another agent already learned. That is not a swarm. That is a crowd. Shared context graphs are what turn agent activity into agent collaboration, and OriginTrail DKG V10 brings them to life. Was just playing with some final polishing for the V10 release, and it is really powerful to see shared context graphs where multiple agents contribute knowledge into the same connected memory, with attribution visible directly in the graph ui. That matters for three reasons. First, agents can access and build on one shared memory instead of staying trapped in isolated sessions. Second, the graph structure helps them retrieve the exact context they need, instead of stuffing everything into a prompt and hoping the model sorts it out. Third, verifiability of provenance. You can see which agent contributed each piece of knowledge, trace the source, and decide what to trust. Tokenmaxxing starts with fewer tokens, but the deeper story is coordination - agents stop reloading the world and start building on shared, verifiable context. That is the foundation for serious multi-agent work across software engineering, research, finance, operations, project management, and far beyond. The future is not more agents, it is agents working from shared, verifiable context. But the more the merrier, of course.

Jurij Skornik

11,180 Aufrufe • vor 4 Monaten

this work from Google engineers is pure f*cking treasure they built WikiSkill: a system that turns an agent's execution history into persistent knowledge, then compiles it into reusable skills this is basically an experience compiler for agents the loop: run tasks ➜ preserve raw traces ➜ consolidate recurring failures + successful strategies into a wiki ➜ propose one atomic skill update ➜ validate ➜ keep or rollback the clever part: skills can roll back the wiki never does successful strategies, recurring failures, rejected edits and skill impact history survive into the next iteration the result is f*cking amazing my takeaway: the next agent memory layer should distill experience into procedures an agent can execute, validate and transfer raw traces ➜ persistent knowledge ➜ validated skills ➜ a better next run save this, then select your gpt-6 astra use case ⭣

this work from Google engineers is pure fcking treasure they built WikiSkill: a system that turns an agent's execution history into persistent knowledge, then compiles it into reusable skills this is basically an experience compiler for agents the loop: run tasks ➜ preserve raw traces ➜ consolidate recurring failures + successful strategies into a wiki ➜ propose one atomic skill update ➜ validate ➜ keep or rollback the clever part: skills can roll back the wiki never does successful strategies, recurring failures, rejected edits and skill impact history survive into the next iteration the result is fcking amazing my takeaway: the next agent memory layer should distill experience into procedures an agent can execute, validate and transfer raw traces ➜ persistent knowledge ➜ validated skills ➜ a better next run save this, then select your gpt-6 astra use case ⭣

beamnxw ./

37,960 Aufrufe • vor 9 Tagen

Jev has been blowing up lately. If you've got the Jev API but don't know how to play around with it yet, you can just copy this checklist. 1. jev-ultrafast A high-speed browser Agent built with Browser Use. Jev only judges "what to do, which element to click" at each step, and only calls the small model when typing is needed. Searching for a flight on Google Flights takes about 7 seconds. 2. fast-jev-compaction Context compression for Claude Code. Before each tool call, have Jev judge if there's anything still useful; delete the useless stuff, and keep the original text without rewriting it. 3. json-render Vercel Labs' generative UI framework. In experiments, Jev doesn't write JSON token by token; it just handles selecting components, properties, and layouts. 4. typesafe-mcp Best for people who just got the API. Plug Jev into Claude Code, Claude Desktop, Codex, and Pi, and do Choice / Score / Noul anytime. 5. jev-mcp Ready-made Agent judgment toolkit: fact-checking, content screening, semantic ranking, classification, and information extraction. 6. SemDecide Turn Jev into a command-line tool. Directly classify, score, and filter in the Shell—great for hooking up to crawlers, CI, and data pipelines. 7. jev-codex-router First have Jev judge how hard this round of programming tasks is, then decide the model tier, reasoning depth, and speed mode. 8. Winnow Context garbage collection for Claude Code. When Read / Bash / Grep spits out a ton of stuff, Jev first judges which parts are really relevant to the current task. 9. jev-review Before code review, run it through Jev first to pick out high-risk changes, then hand them off to a pricier big model or a human. Comes with a local dashboard. 10. Blink Use Jev as a code repository navigator. At each directory level, judge which files are most relevant to the current issue, then keep digging down. Copy these complete Jev blueprints - then read full Jev setup below ↓ ↓

Jev has been blowing up lately. If you've got the Jev API but don't know how to play around with it yet, you can just copy this checklist. 1. jev-ultrafast A high-speed browser Agent built with Browser Use. Jev only judges "what to do, which element to click" at each step, and only calls the small model when typing is needed. Searching for a flight on Google Flights takes about 7 seconds. 2. fast-jev-compaction Context compression for Claude Code. Before each tool call, have Jev judge if there's anything still useful; delete the useless stuff, and keep the original text without rewriting it. 3. json-render Vercel Labs' generative UI framework. In experiments, Jev doesn't write JSON token by token; it just handles selecting components, properties, and layouts. 4. typesafe-mcp Best for people who just got the API. Plug Jev into Claude Code, Claude Desktop, Codex, and Pi, and do Choice / Score / Noul anytime. 5. jev-mcp Ready-made Agent judgment toolkit: fact-checking, content screening, semantic ranking, classification, and information extraction. 6. SemDecide Turn Jev into a command-line tool. Directly classify, score, and filter in the Shell—great for hooking up to crawlers, CI, and data pipelines. 7. jev-codex-router First have Jev judge how hard this round of programming tasks is, then decide the model tier, reasoning depth, and speed mode. 8. Winnow Context garbage collection for Claude Code. When Read / Bash / Grep spits out a ton of stuff, Jev first judges which parts are really relevant to the current task. 9. jev-review Before code review, run it through Jev first to pick out high-risk changes, then hand them off to a pricier big model or a human. Comes with a local dashboard. 10. Blink Use Jev as a code repository navigator. At each directory level, judge which files are most relevant to the current issue, then keep digging down. Copy these complete Jev blueprints - then read full Jev setup below ↓ ↓

rody

194,422 Aufrufe • vor 3 Tagen

HERMES AGENT LEARNS FROM ITS OWN MISTAKES. UPDATES ITS MEMORY. CREATES ITS OWN SKILLS. NO CLOUD. EVERYTHING STORED LOCALLY. THIS IS HOW THE SELF-IMPROVING LOOP WORKS. most agents start from zero every session. Hermes carries forward what it learned. THREE MEMORY SYSTEMS: 1. PROCEDURAL MEMORY (how to act) stored in ~/.hermes/skills/ as SKILL.md files. when the agent repeats a complex workflow, it saves the procedure as a reusable skill. next time the same task comes up, it follows the skill instead of figuring it out again. you can also create skills explicitly: "create a skill called video-prep that captures how I format my video scripts. spoken english, define jargon inline, no em-dashes, close with a catchphrase." the agent writes the SKILL.md. available as a slash command from that moment. Hermes ships with 90+ skills. the number grows the longer you use it. 2. SEMANTIC MEMORY (durable facts about you) stored in ~/.hermes/memory/memory.md the agent scans conversations for facts worth remembering. preferences, habits, corrections, project details. real example from the video: agent tried to scrape a YouTube channel. URL was wrong. it failed. it updated memory.md with the correct URL pattern so it never makes the same mistake again. you can also save explicitly: "save to memory that my favorite testing framework is pytest" the agent updates memory.md immediately. this file loads into context on every session. the agent knows you better every week. 3. EPISODIC MEMORY (chat history) stored in ~/.hermes/state.db (local SQLite). every conversation. every tool call. every result. searchable with FTS5 full-text search. "search our past sessions. what was the first thing I ever said to you?" the agent queries state.db and finds it. over time, auxiliary models consolidate episodic memory into semantic memory. distilling recurring patterns into durable facts. THE SELF-IMPROVING LOOP: every agent run follows this cycle: → you send a prompt → working memory loads: SOUL.md + memory.md + relevant skills + chat history → agent calls tools (terminal, browser, delegate_task) → agent completes the task, replies to you → AFTER the reply: agent checks "did I learn something worth saving?" → if yes: updates memory.md or creates a new skill → next session starts smarter than the last this happens automatically. you don't ask the agent to learn. it decides what to remember on its own. WHAT MAKES THIS DIFFERENT FROM CLAUDE CODE: Claude Code has memory too. but Hermes stores everything locally. no cloud. your data never leaves your machine. Claude Code doesn't auto-create skills from experience. Hermes turns repeated workflows into reusable procedures. Claude Code memory is instruction-based. Hermes memory is conversational and self-updating. over months of usage, Hermes builds a knowledge base of your preferences, your projects, your mistakes, and the procedures that work for your specific workflow. the agent that remembers your birthday also remembers why your last deploy failed. NO EMBEDDINGS. PLAIN TEXT. Hermes does not use embeddings or RAG for memory. skill and memory search runs on plain text keyword matching. simpler. faster. no vector database to maintain. works entirely offline on your local machine. DELEGATE TO CLAUDE CODE: Hermes can spawn a sub-agent that runs Claude Code in headless mode: "spawn a sub-agent using Claude CLI to build a Python script that fetches the top 5 Hacker News stories to markdown." Hermes delegates. Claude Code writes the code. result returns to Hermes. Hermes runs the script and delivers the output. use Hermes for orchestration. use Claude Code for heavy coding. both tools. not competitors. WHAT HERMES DOES NOT HAVE: no built-in eval or LMOps system. no LangSmith, no LangFuse integration out of the box. trajectory export and logs exist but there is no automated quality tracking. if you need eval, build it yourself or connect external tools. the loop is self-improving. measuring how well it improves is on you. comment LOOP and I'll send you the configs that control how fast Hermes learns and what it remembers. memory limits, skill auto-creation triggers, and the auxiliary model that runs the learning. Replace your entire team with 8 hermes agents👇

HERMES AGENT LEARNS FROM ITS OWN MISTAKES. UPDATES ITS MEMORY. CREATES ITS OWN SKILLS. NO CLOUD. EVERYTHING STORED LOCALLY. THIS IS HOW THE SELF-IMPROVING LOOP WORKS. most agents start from zero every session. Hermes carries forward what it learned. THREE MEMORY SYSTEMS: 1. PROCEDURAL MEMORY (how to act) stored in ~/.hermes/skills/ as SKILL.md files. when the agent repeats a complex workflow, it saves the procedure as a reusable skill. next time the same task comes up, it follows the skill instead of figuring it out again. you can also create skills explicitly: "create a skill called video-prep that captures how I format my video scripts. spoken english, define jargon inline, no em-dashes, close with a catchphrase." the agent writes the SKILL.md. available as a slash command from that moment. Hermes ships with 90+ skills. the number grows the longer you use it. 2. SEMANTIC MEMORY (durable facts about you) stored in ~/.hermes/memory/memory.md the agent scans conversations for facts worth remembering. preferences, habits, corrections, project details. real example from the video: agent tried to scrape a YouTube channel. URL was wrong. it failed. it updated memory.md with the correct URL pattern so it never makes the same mistake again. you can also save explicitly: "save to memory that my favorite testing framework is pytest" the agent updates memory.md immediately. this file loads into context on every session. the agent knows you better every week. 3. EPISODIC MEMORY (chat history) stored in ~/.hermes/state.db (local SQLite). every conversation. every tool call. every result. searchable with FTS5 full-text search. "search our past sessions. what was the first thing I ever said to you?" the agent queries state.db and finds it. over time, auxiliary models consolidate episodic memory into semantic memory. distilling recurring patterns into durable facts. THE SELF-IMPROVING LOOP: every agent run follows this cycle: → you send a prompt → working memory loads: SOUL.md + memory.md + relevant skills + chat history → agent calls tools (terminal, browser, delegate_task) → agent completes the task, replies to you → AFTER the reply: agent checks "did I learn something worth saving?" → if yes: updates memory.md or creates a new skill → next session starts smarter than the last this happens automatically. you don't ask the agent to learn. it decides what to remember on its own. WHAT MAKES THIS DIFFERENT FROM CLAUDE CODE: Claude Code has memory too. but Hermes stores everything locally. no cloud. your data never leaves your machine. Claude Code doesn't auto-create skills from experience. Hermes turns repeated workflows into reusable procedures. Claude Code memory is instruction-based. Hermes memory is conversational and self-updating. over months of usage, Hermes builds a knowledge base of your preferences, your projects, your mistakes, and the procedures that work for your specific workflow. the agent that remembers your birthday also remembers why your last deploy failed. NO EMBEDDINGS. PLAIN TEXT. Hermes does not use embeddings or RAG for memory. skill and memory search runs on plain text keyword matching. simpler. faster. no vector database to maintain. works entirely offline on your local machine. DELEGATE TO CLAUDE CODE: Hermes can spawn a sub-agent that runs Claude Code in headless mode: "spawn a sub-agent using Claude CLI to build a Python script that fetches the top 5 Hacker News stories to markdown." Hermes delegates. Claude Code writes the code. result returns to Hermes. Hermes runs the script and delivers the output. use Hermes for orchestration. use Claude Code for heavy coding. both tools. not competitors. WHAT HERMES DOES NOT HAVE: no built-in eval or LMOps system. no LangSmith, no LangFuse integration out of the box. trajectory export and logs exist but there is no automated quality tracking. if you need eval, build it yourself or connect external tools. the loop is self-improving. measuring how well it improves is on you. comment LOOP and I'll send you the configs that control how fast Hermes learns and what it remembers. memory limits, skill auto-creation triggers, and the auxiliary model that runs the learning. Replace your entire team with 8 hermes agents👇

YanXbt

22,720 Aufrufe • vor 2 Monaten

A GROK ENGINEER JUST SHOWED HOW TO MAKE AGENTS IMPROVE THEMSELVES AFTER EVERY RUN most agents lose useful feedback when a task ends: what failed, what changed, and which fix actually worked grok can run 2 loops at once → one handles the task → the other reviews the result → extracts the lesson → stores it for the next run instead of expanding one giant prompt, feedback can be saved as small reusable memory files. one solid correction can help across 10 future tasks research, coding, debugging, and review get more consistent when each run can reuse context and lessons from earlier work this is the shift from repeating the same corrections to building an agent that can reuse what it already learned. bookmark this.

A GROK ENGINEER JUST SHOWED HOW TO MAKE AGENTS IMPROVE THEMSELVES AFTER EVERY RUN most agents lose useful feedback when a task ends: what failed, what changed, and which fix actually worked grok can run 2 loops at once → one handles the task → the other reviews the result → extracts the lesson → stores it for the next run instead of expanding one giant prompt, feedback can be saved as small reusable memory files. one solid correction can help across 10 future tasks research, coding, debugging, and review get more consistent when each run can reuse context and lessons from earlier work this is the shift from repeating the same corrections to building an agent that can reuse what it already learned. bookmark this.

Gipp 🦅

25,540 Aufrufe • vor 15 Tagen

Hermes agent just left the terminal. 𝗛𝗲𝗿𝗺𝗲𝘀 𝗗𝗲𝘀𝗸𝘁𝗼𝗽 dropped yesterday. native app for macOS, Windows, and Linux. for months Hermes was the agent that learned your projects, wrote its own skills, and built a model of who you are. all of it buried in terminal logs. now it has a window. the important part is that it's not a wrapper. it runs the same agent core, the same sessions, memory, and skills as the CLI. you can start a task in the terminal and finish it in the app without anything resetting. the state is shared across every interface, not copied between them. what the GUI actually adds: → streaming chat that shows live tool calls and inline reasoning instead of a spinner → a preview rail that renders pages, code, and images right beside the conversation → an artifacts panel that collects every file the agent has ever produced → remote gateway mode, so you can point the app at a VPS and run the heavy work elsewhere → skills, cron, profiles, and gateways managed point-and-click instead of through YAML → voice mode, drag-drop files, and inline image generation remote gateway mode is the one worth slowing down on. the agent runs 24/7 on a $5 server while you control it from your laptop like a local app. other agent UIs are chatboxes with a logo. this one shows the autonomy instead of hiding it, so you watch the skills load, the tools fire, and the artifacts pile up as it works. it was teased in Jensen's GTC keynote. MIT licensed, local-first, no telemetry. if you already run Hermes, download it and everything is already there. your chats, memory, and skills carry straight over. i wrote a full masterclass on Hermes Agent that walks through the SOUL. md identity layer, the three-tier memory system, the self-evolving skills loop, and how to run three specialized agents 24/7. desktop is the interface that finally does all of it justice. the article is quoted below.

Akshay 🚀

51,540 Aufrufe • vor 3 Monaten

Obsidian CEO actually released the skill that lets your AI agent run your entire vault for you. It's called obsidian-skills. Install it into Claude Code, Codex, or OpenCode, and your agent can read, create, search, and organize notes directly, plus handle Markdown, Bases, and Canvas files without you touching a thing. This is the missing piece for an AI second brain. Your notes live in Obsidian, and now the agent actually knows how to work them. Want the full picture? We broke down how to build a complete AI second brain from scratch in the article below.

Obsidian CEO actually released the skill that lets your AI agent run your entire vault for you. It's called obsidian-skills. Install it into Claude Code, Codex, or OpenCode, and your agent can read, create, search, and organize notes directly, plus handle Markdown, Bases, and Canvas files without you touching a thing. This is the missing piece for an AI second brain. Your notes live in Obsidian, and now the agent actually knows how to work them. Want the full picture? We broke down how to build a complete AI second brain from scratch in the article below.

Simplifying AI

68,025 Aufrufe • vor 1 Monat

🚂 Introducing Agent Prompt Train 🚂 An open-sourced high-performance proxy that works with Claude Code to help turn it from a single-developer tool into a collaborative development platform. Claude Code changed the game. Now, Agent Prompt Train is here to help teams: ✅ Log every conversation for review ✅ Analyze & optimize prompts with AI ✅ Turn best practices into reusable team commands ✨ The payoff: Smarter prompts, faster learning, and shared knowledge across your whole team. 📖 Read more on the blog & test it out 👇

🚂 Introducing Agent Prompt Train 🚂 An open-sourced high-performance proxy that works with Claude Code to help turn it from a single-developer tool into a collaborative development platform. Claude Code changed the game. Now, Agent Prompt Train is here to help teams: ✅ Log every conversation for review ✅ Analyze & optimize prompts with AI ✅ Turn best practices into reusable team commands ✨ The payoff: Smarter prompts, faster learning, and shared knowledge across your whole team. 📖 Read more on the blog & test it out 👇

Moonsong Labs 🌙

21,518 Aufrufe • vor 1 Jahr

Xiaomi just dropped a FREE CLAUDE CODE with memory that actually persists between sessions and nobody is talking about it MiMo Code dropped 4 days ago. 8k GitHub stars. Built-in free model called MiMo Auto - you just install it and it works, zero configuration, zero API keys What's inside: > persistent memory across sessions - agent picks up exactly where it stopped > subagents that spawn automatically and run in parallel > /dream extracts knowledge from your session into project memory > /distill turns your repeated workflows into reusable skills > /goal with a judge model that decides if the work is actually done - not just if the agent thinks it is How to install: > Mac / Linux: curl -fsSL | bash > Windows npm install -g MIMO-ai/cli Then run: > mimo video of me installing and running it is attached github(.)com/XiaomiMiMo/MiMo-Code

Xiaomi just dropped a FREE CLAUDE CODE with memory that actually persists between sessions and nobody is talking about it MiMo Code dropped 4 days ago. 8k GitHub stars. Built-in free model called MiMo Auto - you just install it and it works, zero configuration, zero API keys What's inside: > persistent memory across sessions - agent picks up exactly where it stopped > subagents that spawn automatically and run in parallel > /dream extracts knowledge from your session into project memory > /distill turns your repeated workflows into reusable skills > /goal with a judge model that decides if the work is actually done - not just if the agent thinks it is How to install: > Mac / Linux: curl -fsSL | bash > Windows npm install -g MIMO-ai/cli Then run: > mimo video of me installing and running it is attached github(.)com/XiaomiMiMo/MiMo-Code

monokern

64,312 Aufrufe • vor 3 Monaten

holy sh*t. this is f**king insane. langchain just documented the missing memory layer for agents that are supposed to improve after every run. instead of stuffing everything into one giant prompt, deep agents can keep long-term memory, reusable skills and lessons from previous tasks. [it takes a few minutes to understand the loop] 1/ run the task 2/ save what actually worked 3/ load that lesson into the next run that’s how an agent stops starting from zero every single time.

holy sh*t. this is f**king insane. langchain just documented the missing memory layer for agents that are supposed to improve after every run. instead of stuffing everything into one giant prompt, deep agents can keep long-term memory, reusable skills and lessons from previous tasks. [it takes a few minutes to understand the loop] 1/ run the task 2/ save what actually worked 3/ load that lesson into the next run that’s how an agent stops starting from zero every single time.

Gipp 🦅

33,406 Aufrufe • vor 16 Tagen

Anthropic's in trouble, again! They spent years building what's now fully open-source. What made Claude feel different from a normal app is that the agent could act inside the interface instead of only talking in a chat box. For instance, Claude Artifacts let an agent render real UI, charts, dashboards, and interactive components that assemble live inside the response. Every major AI product tried to replicate it. But the problem was that unlike reasoning, planning, tool-calling, etc., none of it shipped natively with LangGraph, CrewAI, or Google ADK. So teams started building an owned version that required engineering the entire interface layer from scratch. Most teams, however, just settled for shipping the agent as a backend API in a chat box since rendering the UI is only one piece of it. To actually make it work, the interface layer also needed real-time streaming, state kept in sync between agent and UI, conversations that persist across sessions, and reconnection when a user refreshes mid-run. CopilotKit🪁 is now the only open-source framework that actually lets you build your own full-stack Claude-like apps. It decouples the agent from the interface, talking over AG-UI (an open protocol for agent-to-user communication). Being a standard protocol, the frontend never needs to know whether it is talking to a LangGraph or a CrewAI agent. You can change the backend anytime and the UI will never notice. In practice, CopilotKit's interface layer gives several pre-implemented React building blocks that wire the agent directly into the app, like: - generative UI, so the agent renders real components instead of text - chat windows, sidebars, and popups, or a fully headless setup - shared state, so the agent and app stay in sync - human-in-the-loop approvals, where the agent waits before acting - persistent threads that store the whole session, including the agent-user interactions and generated UI, not just text And because that full history is captured, those interactions can feed a self-learning layer that also improves the agent from real usage over time. The interface layer that Anthropic spent years engineering in-house is now literally available to any developer/team. CopilotKit is open-source with 30k+ GitHub stars, and AG-UI, the protocol underneath, is already supported across every major agent framework: LangGraph, CrewAI, Mastra, Google ADK, and more. CopilotKit GitHub repo → (don't forget to star it ⭐ ) If you want to go deeper, I found a detailed breakdown by Shubham Saboo recently on the three Generative UI patterns, with implementation. Read it below.

Anthropic's in trouble, again! They spent years building what's now fully open-source. What made Claude feel different from a normal app is that the agent could act inside the interface instead of only talking in a chat box. For instance, Claude Artifacts let an agent render real UI, charts, dashboards, and interactive components that assemble live inside the response. Every major AI product tried to replicate it. But the problem was that unlike reasoning, planning, tool-calling, etc., none of it shipped natively with LangGraph, CrewAI, or Google ADK. So teams started building an owned version that required engineering the entire interface layer from scratch. Most teams, however, just settled for shipping the agent as a backend API in a chat box since rendering the UI is only one piece of it. To actually make it work, the interface layer also needed real-time streaming, state kept in sync between agent and UI, conversations that persist across sessions, and reconnection when a user refreshes mid-run. CopilotKit🪁 is now the only open-source framework that actually lets you build your own full-stack Claude-like apps. It decouples the agent from the interface, talking over AG-UI (an open protocol for agent-to-user communication). Being a standard protocol, the frontend never needs to know whether it is talking to a LangGraph or a CrewAI agent. You can change the backend anytime and the UI will never notice. In practice, CopilotKit's interface layer gives several pre-implemented React building blocks that wire the agent directly into the app, like: - generative UI, so the agent renders real components instead of text - chat windows, sidebars, and popups, or a fully headless setup - shared state, so the agent and app stay in sync - human-in-the-loop approvals, where the agent waits before acting - persistent threads that store the whole session, including the agent-user interactions and generated UI, not just text And because that full history is captured, those interactions can feed a self-learning layer that also improves the agent from real usage over time. The interface layer that Anthropic spent years engineering in-house is now literally available to any developer/team. CopilotKit is open-source with 30k+ GitHub stars, and AG-UI, the protocol underneath, is already supported across every major agent framework: LangGraph, CrewAI, Mastra, Google ADK, and more. CopilotKit GitHub repo → (don't forget to star it ⭐ ) If you want to go deeper, I found a detailed breakdown by Shubham Saboo recently on the three Generative UI patterns, with implementation. Read it below.

Avi Chawla

460,985 Aufrufe • vor 3 Monaten

Coding agents waste a lot of tokens just figuring out how a site is structured before they can touch it. Map it once instead. Agentmap crawls any site and turns it into a structured map, pages, flows, and the data on each, that any agent loads in one shot. claude code, cursor, a browser agent, all of them skip the blind exploration and go straight to the task. Open source, powered by hyperbrowser ↓

Coding agents waste a lot of tokens just figuring out how a site is structured before they can touch it. Map it once instead. Agentmap crawls any site and turns it into a structured map, pages, flows, and the data on each, that any agent loads in one shot. claude code, cursor, a browser agent, all of them skip the blind exploration and go straight to the task. Open source, powered by hyperbrowser ↓

Hyperbrowser

15,604 Aufrufe • vor 2 Monaten