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.

Ex-Google engineer built a graph-based workflow that made Claude Code do nearly 10 days of work in about an hour. Here's the exact setup he uses. step 1. create a separate Git worktree for every task. run: git worktree add ../task-1 -b task-1 open a new terminal, cd into... it, and launch Claude Code. repeat this for every agent. each one gets its own branch, so nothing conflicts. step 2. give every Claude agent a different task. same repository. different branches. they all work in parallel. step 3. once they're done, review the pull requests. keep the good ones. merge what works. step 4. add a review agent. paste each PR into Claude and ask: "does this implementation match the original specification" every agent now has another agent reviewing its work before it gets merged. step 5. scale it up. 48GB of RAM can comfortably run around 20 Claude Code agents. 128GB can handle roughly 50. most engineers run Claude Code once and wait. he runs dozens of Claude Code agents in parallel, then merges the best results. this 60-minute lecture is one of the best free resources on graph engineering and multi-agent workflows. bookmark it and watch it below.show more

MIKE

27,922 subscribers

32,313 views • 3 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

27 Comments

Sesori - Claude, Codex & OpenCode on Mobile3 months ago

At 20 agents, launching them isn't the hard part. Knowing which one needs you before merge time is.

Alek Poniatowski3 months ago

This is exactly how you build in codex by default. Its support for worktrees is amazing

Sakata3 months ago

Bookmarkedddd will watch when I’m free

Liam | AI Tools & News3 months ago

Helpful

MIKE3 months ago

I’m happy to hear that

MAIL3 months ago

damn great step by step guide

安叫兽|Bird🕊️ 🔶 BNB3 months ago

worktree 这招真挺适合并行折腾的

Vipul Kumar Kewat3 months ago

This is a great example of using AI to parallelize software development instead of treating it like a single coding assistant. Breaking work into independent task and adding a review step makes the workflow mouch more scalable and reliable.

DAVE3 months ago

oh wow

Coscosmico3 months ago

worktrees plus a review agent is the part people skip when they brag about agent headcount

Diario฿itcoin3 months ago

All I see is merge hell.

Jurly3 months ago

This is the kind of workflow optimization that makes me think we're still in the early days of understanding how to best

LarpRom3 months ago

Good orchestration beats throwing everything at one agent.

Blum3 months ago

cutting 10 days of work down to an hour is insanely effective

creeeeng3 months ago

stack bloat feels productive lol tbh

FlowOps Daily3 months ago

“每个任务一个 git worktree” 这一步特别关键，因为后面不只是并行，更是验收不串。一个 worktree 对一张任务单、一个 diff、一个 rollback 点，review 时连 comment 漂移都会少很多。很多人觉得 graph engineering 难，先把这层隔离做好，后面的 agent 分工才不会越跑越乱。

unchosen.eth3 months ago

the review agent is my favorite part

cbrd21-1("bird")3 months ago

i do this with a distributed control plane that coordinates all the work onto many machines-scales horizontal and vertical and can use pi with local or openrouter or nim free models even and/or claude code-u can mix n match and it autoscales and autoheals

Abdulmuiz Adeyemo3 months ago

Oh man this is a huge Graph Engineering Masterclass

The AI Therapist3 months ago

Graph-based workflow = 10 days in 1 hour. the prompt engineering grind is over. the prompt orchestration monopoly is starting.

ceek3 months ago

let’s get it

𝐕𝖆𝖑𝖊𝖓𝖙𝖎𝖓𝖔~❍𝖓𝖈𝖍𝖆𝖎𝖓.𓄀3 months ago

Alot of steps.

catman3 months ago

using separate git worktrees for each task is clever. keeps the claude agent isolated so one failure doesn’t derail the other nine.

Leo3 months ago

smooth workflow here mate

Innopro3 months ago

What they built is interesting

stanley3 months ago

insane work jesus.

mike3 months ago

wow insane bro bookmarked

Related Videos

THIS IS HOW A SENIOR ENGINEER ACTUALLY SCALES THEMSELVES WITH CLAUDE CODE the biggest change with AI isn't coding faster. it's where you actually spend your time now. more detailed prompts, more code review, more planning, less typing, etc. here's the workflow: this guy has been shipping code since the days of cgi and perl. he uses a compound engineering plugin that runs 5 separate agents on every task. one brainstorms, one plans the technical implementation, one executes, one reviews, one checks different verticals. every step is documented in markdown files. it's slow and way more waiting. but the output quality is way higher because each agent is focused on one thing. then the REAL multiplier is in git worktrees if Claude Code made you 10x faster, worktrees multiplies that again depending on how many agents you can manage in parallel his team runs 4-8 Claude Code sessions at the same time across different worktrees with each one working on a separate task. the skill is managing multiple AI agents in parallel without losing track, that's the next evolution of engineering

THIS IS HOW A SENIOR ENGINEER ACTUALLY SCALES THEMSELVES WITH CLAUDE CODE the biggest change with AI isn't coding faster. it's where you actually spend your time now. more detailed prompts, more code review, more planning, less typing, etc. here's the workflow: this guy has been shipping code since the days of cgi and perl. he uses a compound engineering plugin that runs 5 separate agents on every task. one brainstorms, one plans the technical implementation, one executes, one reviews, one checks different verticals. every step is documented in markdown files. it's slow and way more waiting. but the output quality is way higher because each agent is focused on one thing. then the REAL multiplier is in git worktrees if Claude Code made you 10x faster, worktrees multiplies that again depending on how many agents you can manage in parallel his team runs 4-8 Claude Code sessions at the same time across different worktrees with each one working on a separate task. the skill is managing multiple AI agents in parallel without losing track, that's the next evolution of engineering

Om Patel

159,908 views • 6 months ago

Maximizing your token throughput is one of the biggest productivity unlocks in Claude Code. So here's my guide to use multiple Claude Codes at the same time, effectively: - Run multiple Claude Code sessions at the same time, each on a different feature (Ghostty is great for this) - Use Claude Code's built in git worktrees to keep each instance isolated on its own branch (-w or --worktree flag) - Let Claude handle creating PRs or merging the worktree branches when you're done - Use the Claude Code Desktop app as your multi-agent control center Full guide below:

Maximizing your token throughput is one of the biggest productivity unlocks in Claude Code. So here's my guide to use multiple Claude Codes at the same time, effectively: - Run multiple Claude Code sessions at the same time, each on a different feature (Ghostty is great for this) - Use Claude Code's built in git worktrees to keep each instance isolated on its own branch (-w or --worktree flag) - Let Claude handle creating PRs or merging the worktree branches when you're done - Use the Claude Code Desktop app as your multi-agent control center Full guide below:

Avthar

10,754 views • 7 months ago

$ANTHROPIC JUST QUIETLY SHIPPED A FEATURE THAT LETS CLAUDE SPAWN A WHOLE TEAM OF AGENTS THAT MESSAGE EACH OTHER AND REVIEW EACH OTHER'S WORK. It's a Claude Code feature called agent teams. The team lead spawns multiple agents that share a task list and message each other directly, not subagents reporting back, actual peers. In the demo a QA agent caught three bugs, sent the work back to the front-end and back-end devs, they fixed it, app shipped in one pass. How to run it: 1. Enable it. Needs Claude Code v2.1.32+. Add to settings.json: "env": { "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1" }. Or paste that to Claude and say "add this to my settings." Restart. 2. Prompt in plain English. Start with a goal (agents wake with zero context), then "create a team of 3 using Sonnet," describe each role, its deliverable, and who it messages when done. 3. The rules: each agent owns its own files, define exact outputs, name who talks to who, keep it to 3-5 agents. Use it for complex work with separate parts running in parallel. Skip it for simple or sequential tasks, teams cost 3-4x the tokens. Bookmark this.$

ANTHROPIC JUST QUIETLY SHIPPED A FEATURE THAT LETS CLAUDE SPAWN A WHOLE TEAM OF AGENTS THAT MESSAGE EACH OTHER AND REVIEW EACH OTHER'S WORK. It's a Claude Code feature called agent teams. The team lead spawns multiple agents that share a task list and message each other directly, not subagents reporting back, actual peers. In the demo a QA agent caught three bugs, sent the work back to the front-end and back-end devs, they fixed it, app shipped in one pass. How to run it: 1. Enable it. Needs Claude Code v2.1.32+. Add to settings.json: "env": { "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1" }. Or paste that to Claude and say "add this to my settings." Restart. 2. Prompt in plain English. Start with a goal (agents wake with zero context), then "create a team of 3 using Sonnet," describe each role, its deliverable, and who it messages when done. 3. The rules: each agent owns its own files, define exact outputs, name who talks to who, keep it to 3-5 agents. Use it for complex work with separate parts running in parallel. Skip it for simple or sequential tasks, teams cost 3-4x the tokens. Bookmark this.

Yarchi

463,029 views • 4 months ago

Claude Code just became a multi-agent powerhouse! Create custom agents like code reviewers and security experts with /agents My workflow: software engineer → code reviewer → security agent. Each specialised agent catches what others might miss 10x'd my productivity by having focused experts review every step. Here's how to set it up:

Claude Code just became a multi-agent powerhouse! Create custom agents like code reviewers and security experts with /agents My workflow: software engineer → code reviewer → security agent. Each specialised agent catches what others might miss 10x'd my productivity by having focused experts review every step. Here's how to set it up:

Mervin Praison

77,604 views • 1 year ago

Cursor for Design? This Claude Code UI workflow is insane And many vibe coders not aware of it: 1. Claude Code can assign parallel tasks to sub agents 2. Integrate with git worktree to create sandbox env This means you can get Claude Code generate 10 design at the same time, fork & iterate 🔁 Design is an explorative process, by leveraging sub agent + parallel task capabilities, many interesting product UX can be built; Also turned this workflow into an open-source IDE extension here:

Cursor for Design? This Claude Code UI workflow is insane And many vibe coders not aware of it: 1. Claude Code can assign parallel tasks to sub agents 2. Integrate with git worktree to create sandbox env This means you can get Claude Code generate 10 design at the same time, fork & iterate 🔁 Design is an explorative process, by leveraging sub agent + parallel task capabilities, many interesting product UX can be built; Also turned this workflow into an open-source IDE extension here:

Jason Zhou

40,635 views • 1 year ago

Kimi CEO Zhilin Yang: "The biggest mistake in agent systems - people trying to build one smarter agent we didn't make one smarter - Kimi made a thousand: one brain, a thousand hands" here's how: step 1 → stop polishing one agent, split the task and run many in parallel - that's the real ceiling-break step 2 → give each agent a long context so it can run for days, not seconds - long context is what lets an agent run long step 3 → give each agent a strong prior, so agent-RL can search for a good solution instead of starting from zero step 4 → don't just add more data - make each token count. they hit the data wall, so they made every token 2x smarter step 5 → don't scale one brain, scale the swarm - many agents working in parallel beat one agent thinking harder he just dropped Kimi K3 - and this 40-min workflow is the best on how to actually use it watch & bookmark - then read the article on saving on agents ↓

Kimi CEO Zhilin Yang: "The biggest mistake in agent systems - people trying to build one smarter agent we didn't make one smarter - Kimi made a thousand: one brain, a thousand hands" here's how: step 1 → stop polishing one agent, split the task and run many in parallel - that's the real ceiling-break step 2 → give each agent a long context so it can run for days, not seconds - long context is what lets an agent run long step 3 → give each agent a strong prior, so agent-RL can search for a good solution instead of starting from zero step 4 → don't just add more data - make each token count. they hit the data wall, so they made every token 2x smarter step 5 → don't scale one brain, scale the swarm - many agents working in parallel beat one agent thinking harder he just dropped Kimi K3 - and this 40-min workflow is the best on how to actually use it watch & bookmark - then read the article on saving on agents ↓

codila

61,321 views • 3 months ago

You can now orchestrate subagents running in Claude Code, Codex, or the Warp Agent. Let the agent create a delegation plan, and watch subagents coordinate with message passing. Each agent gets its own worktree for isolation. Here's how it works with eng Matthew Albright:

You can now orchestrate subagents running in Claude Code, Codex, or the Warp Agent. Let the agent create a delegation plan, and watch subagents coordinate with message passing. Each agent gets its own worktree for isolation. Here's how it works with eng Matthew Albright:

Warp

20,810 views • 5 months ago

Claude Code tip: create an agent that specialises in code review and security. Then add a new memory entry with a nickname for it so you can call it anytime. My code review and security agent is called Big Tony.

Claude Code tip: create an agent that specialises in code review and security. Then add a new memory entry with a nickname for it so you can call it anytime. My code review and security agent is called Big Tony.

Richie

135,574 views • 9 months ago

Review code written by one agent using a different agent entirely. Here, Claude handles the task, and Gemini runs the review, leaves inline comments, and sends them back to the original agent to implement. Any combination works.

Review code written by one agent using a different agent entirely. Here, Claude handles the task, and Gemini runs the review, leaves inline comments, and sends them back to the original agent to implement. Any combination works.

Air by JetBrains

22,981,917 views • 5 months ago

this is pure f*cking treasure 10 GitHub repos with 165K+ combined stars to build your own AI agent team that works 24/7 most people still use one AI chat for everything. these repos turn Claude into a whole team: one agent researches, one codes, one reviews, and a lead runs them all one resource per step, from your first 3 agents to a full swarm running Claude and Codex together (1/10) CrewAI the easiest way to assemble a team of agents: give them roles and tasks, then hit kickoff ▸ (2/10) LangGraph connect agents into a graph with checkpoints, so if something fails it resumes instead of starting over ▸ (3/10) wshobson/agents ready-made agents for Claude Code (backend, frontend, security, tests, devops) plus an orchestrator to run them ▸ (4/10) oh-my-team 12 specialist agents for Claude Code that split the work and merge the results ▸ (5/10) agent-swarm your own self-hosted AI company: one lead agent hires workers and runs them 24/7 ▸ (6/10) Open-Agents spawns many Claude agents in parallel, so 6 tasks run at once instead of one after another ▸ (7/10) swarms an enterprise-grade framework for when your team grows from 5 agents to 50 ▸ (8/10) Microsoft Agent Framework Microsoft's new framework, the AutoGen successor, for workflows, agents and runtime in one place ▸ (9/10) CLI Agent Orchestrator runs Claude, Codex and other CLIs side by side as one team, with a supervisor watching all of them ▸ (10/10) ensemble launches Codex and Claude together, so they build and ship as one ▸ the loop: assemble → plug in → run → scale → orchestrate pick one, click, let it run, and while everyone else is still typing prompts, your agents are already shipping ↓

this is pure f*cking treasure 10 GitHub repos with 165K+ combined stars to build your own AI agent team that works 24/7 most people still use one AI chat for everything. these repos turn Claude into a whole team: one agent researches, one codes, one reviews, and a lead runs them all one resource per step, from your first 3 agents to a full swarm running Claude and Codex together (1/10) CrewAI the easiest way to assemble a team of agents: give them roles and tasks, then hit kickoff ▸ (2/10) LangGraph connect agents into a graph with checkpoints, so if something fails it resumes instead of starting over ▸ (3/10) wshobson/agents ready-made agents for Claude Code (backend, frontend, security, tests, devops) plus an orchestrator to run them ▸ (4/10) oh-my-team 12 specialist agents for Claude Code that split the work and merge the results ▸ (5/10) agent-swarm your own self-hosted AI company: one lead agent hires workers and runs them 24/7 ▸ (6/10) Open-Agents spawns many Claude agents in parallel, so 6 tasks run at once instead of one after another ▸ (7/10) swarms an enterprise-grade framework for when your team grows from 5 agents to 50 ▸ (8/10) Microsoft Agent Framework Microsoft's new framework, the AutoGen successor, for workflows, agents and runtime in one place ▸ (9/10) CLI Agent Orchestrator runs Claude, Codex and other CLIs side by side as one team, with a supervisor watching all of them ▸ (10/10) ensemble launches Codex and Claude together, so they build and ship as one ▸ the loop: assemble → plug in → run → scale → orchestrate pick one, click, let it run, and while everyone else is still typing prompts, your agents are already shipping ↓

Noisy

14,563 views • 11 days ago

Claude Tag is the next evolution of agents. It's a proactive, multiplayer agent with memory and identity, built on top of Claude Code. Learn more about how Claude Tag works and best practices for using it in this deep dive.

Claude Tag is the next evolution of agents. It's a proactive, multiplayer agent with memory and identity, built on top of Claude Code. Learn more about how Claude Tag works and best practices for using it in this deep dive.

ClaudeDevs

454,269 views • 4 months ago

Claude Opus 5.5 just hacked my TV box and turned it into Mac Mini... my AI agents now run 24/7 on free box from my TV provider while I sleep (every step on video) 1 reverse-engineering prompt + guide below = you don't need $899 Mac Mini: step 1 → that box behind your TV is a Linux computer, Claude does the thinking in the cloud, TV box just runs the tools step 2 → Claude Code x-rays it from prompt below + one photo step 3 → it installs a real Linux shell built for your chip, many boxes run 32-bit Android, so the wrong build won't even install step 4 → then it adds a wake lock + battery whitelist, so Android can't kill your agent in the background like normal apps step 5 → it wires the agent to your own Telegram bot: answers only you, zero open ports, your API key never touches the chat step 6 → close your laptop and set a task once, it runs all night with zero babysitting step 7 → optional: hook your TV up as a live terminal and watch the agent think and write every line of code in real time the result: $899 Mac Mini is faster with 8x the RAM, but for small 24/7 AI tasks - TV box does the job (but 8 TV boxes still cost less than one $899 Mac Mini) p.s: this methodworks on Android TV, Google TV and Fire TV boxes on Android 7+, mine has just 2 GB of RAM different box? let Claude Code figure it out Run it today. Then read article below on how to reverse-engineer anything:

Claude Opus 5.5 just hacked my TV box and turned it into Mac Mini... my AI agents now run 24/7 on free box from my TV provider while I sleep (every step on video) 1 reverse-engineering prompt + guide below = you don't need $899 Mac Mini: step 1 → that box behind your TV is a Linux computer, Claude does the thinking in the cloud, TV box just runs the tools step 2 → Claude Code x-rays it from prompt below + one photo step 3 → it installs a real Linux shell built for your chip, many boxes run 32-bit Android, so the wrong build won't even install step 4 → then it adds a wake lock + battery whitelist, so Android can't kill your agent in the background like normal apps step 5 → it wires the agent to your own Telegram bot: answers only you, zero open ports, your API key never touches the chat step 6 → close your laptop and set a task once, it runs all night with zero babysitting step 7 → optional: hook your TV up as a live terminal and watch the agent think and write every line of code in real time the result: $899 Mac Mini is faster with 8x the RAM, but for small 24/7 AI tasks - TV box does the job (but 8 TV boxes still cost less than one $899 Mac Mini) p.s: this methodworks on Android TV, Google TV and Fire TV boxes on Android 7+, mine has just 2 GB of RAM different box? let Claude Code figure it out Run it today. Then read article below on how to reverse-engineer anything:

codila

55,706 views • 8 days ago

There's a built-in agent inside Claude Code you can invoke just by telling Claude to use the claude-code-guide agent Save this... you'll need it It's not a local file in your project. It's a built-in subagent defined in Claude Code's system itself. It answers questions about Claude Code CLI, the Agent SDK, and the Claude API. It uses Glob, Grep, Read, WebFetch, and WebSearch, but can't edit or write files. Its only job is to answer questions.

There's a built-in agent inside Claude Code you can invoke just by telling Claude to use the claude-code-guide agent Save this... you'll need it It's not a local file in your project. It's a built-in subagent defined in Claude Code's system itself. It answers questions about Claude Code CLI, the Agent SDK, and the Claude API. It uses Glob, Grep, Read, WebFetch, and WebSearch, but can't edit or write files. Its only job is to answer questions.

Daniel San

57,445 views • 7 months ago

ANTHROPIC ENGINEER DROPPED A 26-MINUTE CLAUDE CODE GUIDE. 99% of people use Claude Code like Google. Bookmark this for the weekend. 26 minutes. Boss Agent. PM Agents. Max value, minimal cost. Prompt → Context → Cache → Model → Effort → Subagents and if you're still deciding which model to run it on, every AI model and what it costs, below ↓

ANTHROPIC ENGINEER DROPPED A 26-MINUTE CLAUDE CODE GUIDE. 99% of people use Claude Code like Google. Bookmark this for the weekend. 26 minutes. Boss Agent. PM Agents. Max value, minimal cost. Prompt → Context → Cache → Model → Effort → Subagents and if you're still deciding which model to run it on, every AI model and what it costs, below ↓

Kirill

176,001 views • 21 days ago

You can now run Claude Code locally for FREE. → Using open-source models → Locally and fully private → Full agent + tool workflows Here's the FULL step-by-step tutorial to get it all set up in less than 10 minutes:

You can now run Claude Code locally for FREE. → Using open-source models → Locally and fully private → Full agent + tool workflows Here's the FULL step-by-step tutorial to get it all set up in less than 10 minutes:

Alvaro Cintas

1,321,113 views • 9 months ago

I pointed the new Claude Managed Agents dynamic workflows at 18k lines of code. > 21 proven bugs. > 5 minutes. > $8.36, on my Claude Max API credits. A lead agent writes a plan, runs it across many agents in phases, then merges the results. Try it in Claude Code: /claude-api managed-agents-onboard bug-hunter It burns tokens fast. It's worth it.

I pointed the new Claude Managed Agents dynamic workflows at 18k lines of code. > 21 proven bugs. > 5 minutes. > $8.36, on my Claude Max API credits. A lead agent writes a plan, runs it across many agents in phases, then merges the results. Try it in Claude Code: /claude-api managed-agents-onboard bug-hunter It burns tokens fast. It's worth it.

Dan McAteer

11,404 views • 18 days ago

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

20,626 views • 2 months ago

Opus 5.5 makes this AI stack look f…cking illegal 10 GitHub repos for building everything around the model 01 zen-mcp-server ▸ → your agent debates Gemini, GPT and local models mid-task 02 claude-context ▸ → semantic code search so the agent stops grepping blind 03 wshobson/agents ▸ → a roster of subagents, each with one narrow job 04 mcp-agent ▸ → workflow patterns built around MCP tools, not around chat 05 Backlog.md ▸ → tasks live in git, so the agent and you read the same board 06 Claude Code Development Kit ▸ → hooks, subagents and MCP wired for context at scale 07 agent-rules ▸ → shared guardrails the agent inherits in every repo 08 Agent Skills ▸ → one file that teaches the agent a job, portable across tools 09 agent-scan ▸ → scans your agents, MCP servers and skills for what leaks 10 awesome-claude-code-toolkit ▸ → the map: agents, skills, commands, hooks, MCP configs the architecture: rules → context → subagents → tools → state → review → scan I'd split the stack like this: context: claude-context → Development Kit work: wshobson/agents → mcp-agent → zen-mcp-server state: Backlog.md safety: agent-rules → Agent Skills → agent-scan everyone posts the SDK and the CLI the layer that decides whether your agent survives a week is this one the model is one folder in the stack ⭣

Opus 5.5 makes this AI stack look f…cking illegal 10 GitHub repos for building everything around the model 01 zen-mcp-server ▸ → your agent debates Gemini, GPT and local models mid-task 02 claude-context ▸ → semantic code search so the agent stops grepping blind 03 wshobson/agents ▸ → a roster of subagents, each with one narrow job 04 mcp-agent ▸ → workflow patterns built around MCP tools, not around chat 05 Backlog.md ▸ → tasks live in git, so the agent and you read the same board 06 Claude Code Development Kit ▸ → hooks, subagents and MCP wired for context at scale 07 agent-rules ▸ → shared guardrails the agent inherits in every repo 08 Agent Skills ▸ → one file that teaches the agent a job, portable across tools 09 agent-scan ▸ → scans your agents, MCP servers and skills for what leaks 10 awesome-claude-code-toolkit ▸ → the map: agents, skills, commands, hooks, MCP configs the architecture: rules → context → subagents → tools → state → review → scan I'd split the stack like this: context: claude-context → Development Kit work: wshobson/agents → mcp-agent → zen-mcp-server state: Backlog.md safety: agent-rules → Agent Skills → agent-scan everyone posts the SDK and the CLI the layer that decides whether your agent survives a week is this one the model is one folder in the stack ⭣

rody

18,089 views • 27 days ago

I can't f*cking believe people still use Claude Code like a chat bot. the ones getting real work out of it gave it a folder, tools and a map of everything it knows. that map is graphify. you point it at a folder and it builds a knowledge graph of everything inside. code, docs, PDFs, images, even video. then your agent searches the graph instead of opening files one by one. 134k stars on GitHub. backed by Y Combinator. and most people still haven't tried it. what makes it different: -> the code part runs fully on your machine. nothing gets uploaded -> no vector database, no embeddings. it's a real graph your agent walks through -> every connection is labeled: read straight from the source, or figured out by graphify. you always know which -> you get 3 files: a clickable map you open in your browser, a report with the key ideas and surprising links, and the full graph your agent queries anytime on a public memory benchmark it found the right answer in its top 10 results about half the time. mem0 managed under 5%. and building the graph cost 0 model credits. here's the full setup around it: > create a folder called AGENT, open Claude Code inside it, and add a CLAUDE.md with one line: "save every decision, person and project to memory/" > run uv tool install graphifyy, then graphify install, then type /graphify . and the whole folder becomes a map Claude can search in seconds > run npm install -g @googleworkspace/cli, then gws auth setup and gws auth login. Claude can now read your Gmail, Calendar and Drive > run claude mcp add playwright npx @playwright/mcp@latest. it gets its own browser for sites, forms and data > run npm i -g jev-guard, then jev-guard key "...", then jev-guard install claude. Jev checks every action before it runs. rm -rf gets blocked, emails with hidden instructions get flagged, about 4 cents per 1,000 checks > type /schedule and say "every morning at 7:30, send me what came in, what you drafted and what needs my yes" one folder. 15 minutes. and Claude finally knows where everything is. all the repos: -> -> -> -> bookmark this and try graphify first. it's the piece everyone skips.

I can't f*cking believe people still use Claude Code like a chat bot. the ones getting real work out of it gave it a folder, tools and a map of everything it knows. that map is graphify. you point it at a folder and it builds a knowledge graph of everything inside. code, docs, PDFs, images, even video. then your agent searches the graph instead of opening files one by one. 134k stars on GitHub. backed by Y Combinator. and most people still haven't tried it. what makes it different: -> the code part runs fully on your machine. nothing gets uploaded -> no vector database, no embeddings. it's a real graph your agent walks through -> every connection is labeled: read straight from the source, or figured out by graphify. you always know which -> you get 3 files: a clickable map you open in your browser, a report with the key ideas and surprising links, and the full graph your agent queries anytime on a public memory benchmark it found the right answer in its top 10 results about half the time. mem0 managed under 5%. and building the graph cost 0 model credits. here's the full setup around it: > create a folder called AGENT, open Claude Code inside it, and add a CLAUDE.md with one line: "save every decision, person and project to memory/" > run uv tool install graphifyy, then graphify install, then type /graphify . and the whole folder becomes a map Claude can search in seconds > run npm install -g @googleworkspace/cli, then gws auth setup and gws auth login. Claude can now read your Gmail, Calendar and Drive > run claude mcp add playwright npx @playwright/mcp@latest. it gets its own browser for sites, forms and data > run npm i -g jev-guard, then jev-guard key "...", then jev-guard install claude. Jev checks every action before it runs. rm -rf gets blocked, emails with hidden instructions get flagged, about 4 cents per 1,000 checks > type /schedule and say "every morning at 7:30, send me what came in, what you drafted and what needs my yes" one folder. 15 minutes. and Claude finally knows where everything is. all the repos: -> -> -> -> bookmark this and try graphify first. it's the piece everyone skips.

kiosa

26,006 views • 2 days ago

Claude Code costs $200/month here's how to run it for free. 4 commands. 10 minutes step 1 - install Ollama runs AI models locally → download from → install. it runs in background on localhost:11434 step 2 - download a coding model → ollama pull qwen2.5-coder:14b (7b for 8GB RAM, 32b for 32GB+ RAM) step 3 - redirect Claude Code to your machine → export ANTHROPIC_BASE_URL= → export ANTHROPIC_MODEL=qwen2.5-coder:14b step 4 - launch → claude → "make a hello world website" → it reads files, writes code, runs commands. locally. free same agent loop. same tools. $0/month the $200 was for convenience the capability was always free like + bookmark - you'll need this

Claude Code costs $200/month here's how to run it for free. 4 commands. 10 minutes step 1 - install Ollama runs AI models locally → download from → install. it runs in background on localhost:11434 step 2 - download a coding model → ollama pull qwen2.5-coder:14b (7b for 8GB RAM, 32b for 32GB+ RAM) step 3 - redirect Claude Code to your machine → export ANTHROPIC_BASE_URL= → export ANTHROPIC_MODEL=qwen2.5-coder:14b step 4 - launch → claude → "make a hello world website" → it reads files, writes code, runs commands. locally. free same agent loop. same tools. $0/month the $200 was for convenience the capability was always free like + bookmark - you'll need this

self.dll

178,272 views • 6 months ago