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.

Agent Zero crushed Codex by 2.6× on token efficiency! We gave both agents the same task on the same local model (Qwen3.6 27B): build a retro Qbert arcade game. Each agent wrote and rewrote it across iterations, adding enemies and a HUD. Outputs: • Agent Zero: 239K tokens, 53... min • Codex: 627K tokens, 51 min Both agents built a working Qbert, but Gitlawb 's Agent Zero is the cleaner build, with crisper textures and hops that land where they should. Codex refills the context window with its whole history every turn, so the model loses the thread and hallucinates code it never wrote. Agent Zero sends only what's new, so it keeps more of the window open and makes fewer mistakes. Run agents on local AI models in Atomic Chat!show more

atomic.chat

18,389 subscribers

320,509 views • 3 months ago •via X (Twitter)

Science & Technology Gaming

Anya Rossi• Live Now

Private livecam show

35 Comments

GitLawb3 months ago

Zero is amazing

atomic.chat3 months ago

Run Local AI Models and agents:

Aman3 months ago

2.6x fewer tokens is actually insane

atomic.chat3 months ago

true. especially when we are speaking about limited context window :)

XiaoXin|201.eth3 months ago

this is @Agent0ai not @gitlawb

aditya3 months ago

Tokens optimisation 🫡

augmented things3 months ago

Wow. That’s great.

🏆🇧🇷💎Jack Hunter 💎 🇧🇷🎖️🥇3 months ago

Cool! @gitlawb’s Zero is great indeed!!

dumbfoundry3 months ago

thanks for sharing, fyi @agent0ai is not from gitlawb

Luis Gamas3 months ago

Zero is hands down one of the best open-source harnesses I've used, imagine being able to invoke it right from your phone 👀👇

Prompt Heat3 months ago

can i use witf gpt-gemini or claude and cline-opencode-Cursor sub in this cli tool???

William Belfort3 months ago

Interesting… 👀

Frosty403 months ago

where is the prompt for this one? would love to test my private harness just to see how it compares.

Rob3 months ago

Agent Zero is still around? The same Agent Zero that came out around the time CrewAI popped up? Neat, might have to revisit them

mardi3 months ago

nice try... the power being showcased in this video is the real agent zero → @Agent0ai interesting that the gitlawb account doesn't even seem to know what its own software looks like

Alessandro Frau3 months ago

Thank you so much for showing Agent Zero capabilities and efficiency 🫶🏼

SSH3 months ago

if you really want the biggest token efficiency boosts then use Grug!

Carter Jiang3 months ago

2.6x fewer tokens and it actually built a working game? That's the real flex. Most "efficient" agents just output less, not better.

Saman Ahmed3 months ago

The token count is only part of the story.

Trần Ngọc Sơn3 months ago

Compare it to the cursor.

Pixel3 months ago

Cleaner context management = fewer hallucinations and better final output.

安叫兽|Bird🕊️ 🔶 BNB3 months ago

时间差不多，token 差这么多挺离谱

稳住拿好等风来3 months ago

@Agent0ai

Jinjala dinesh3 months ago

Please fight on terminal bench

Mark R Pommrehn3 months ago

Nice!

Epoch Lens | AI & Tech3 months ago

Codex used 388K extra tokens to finish 2 minutes faster. The agentic equivalent of running git log -p --all before changing 1 line.

euxaristia3 months ago

Better output, less tokens. Zero is goated

BeastTitanHunter3 months ago

@thsottiaux @OpenAI !!!!!

Dany Boy3 months ago

@grok what music is this? Love it

AshutoshShrivastava3 months ago

agent architecture matters a lot .

Michael3 months ago

Agent One crushed Agent Zero by 5x on token efficiency

AI Mastery Guide3 months ago

Only sending what's new instead of the whole history is such a clean fix.

Carry3 months ago

one benchmark on a retro game and the headline is 2.6x lol what does this look like on something with real dependencies 😐

Amitakshya Sutar3 months ago

@all Can anyone tell me what font is used for that zero ? I’m kind of obsessed with that style of art.

AAD3 months ago

It’s not @gitlawb btw, it’s a fork of agent zero (real one)

Related Videos

OpenHands crushed Codex by 2.3× on token efficiency! We gave both agents the same task on the same model (Qwen3.5 35B): build an 8-bit Space Invaders in 3 iterations (build, fix, polish). Output: • OpenHands: 219K tokens, • Codex: 513K tokens, OpenHands beats Codex in local running. The difference is in how they handle context. OpenHands reuses the unchanged data across every pass and only pays for new tokens, while Codex re-sends and re-counts it every iteration. OpenHands finished a bit slower, but on local runs, tokens spent are the real cost.

OpenHands crushed Codex by 2.3× on token efficiency! We gave both agents the same task on the same model (Qwen3.5 35B): build an 8-bit Space Invaders in 3 iterations (build, fix, polish). Output: • OpenHands: 219K tokens, • Codex: 513K tokens, OpenHands beats Codex in local running. The difference is in how they handle context. OpenHands reuses the unchanged data across every pass and only pays for new tokens, while Codex re-sends and re-counts it every iteration. OpenHands finished a bit slower, but on local runs, tokens spent are the real cost.

atomic.chat

29,842 views • 3 months ago

Go from idea to a working agent faster with the Agents API. Build and run cloud agents with the Codex harness, fully managed by OpenAI. We handle orchestration, long-running sessions, and context management. You focus on what makes your agent unique. Available in public beta.

Go from idea to a working agent faster with the Agents API. Build and run cloud agents with the Codex harness, fully managed by OpenAI. We handle orchestration, long-running sessions, and context management. You focus on what makes your agent unique. Available in public beta.

OpenAI Developers

1,939,993 views • 1 month ago

Introducing October, the world's most advanced agent orchestrator Claude? Codex? Grok? Cursor? Which model? Which harness? How much quota is left? You shouldn't have to care Give October a task. It builds the team, connects the agents with native agent agent comms, and orchestrates the work based on the task, your taste, budget and remaining usage (or build the team yourself) And it's multiplayer: your team's agents can work with yours, live on the same canvas

Introducing October, the world's most advanced agent orchestrator Claude? Codex? Grok? Cursor? Which model? Which harness? How much quota is left? You shouldn't have to care Give October a task. It builds the team, connects the agents with native agent agent comms, and orchestrates the work based on the task, your taste, budget and remaining usage (or build the team yourself) And it's multiplayer: your team's agents can work with yours, live on the same canvas

Harsh Savergaonkar

26,343 views • 1 month ago

Claude Code vs Agent Zero, same model: Claude Opus 5 High, released yesterday. Build a working Web OS from scratch. Terminal, apps, two games. Claude Code: 9:58, 80.3k tokens Agent Zero: 11:34, 59.7k tokens That's 26% fewer tokens for the same result. Full test at the end

Claude Code vs Agent Zero, same model: Claude Opus 5 High, released yesterday. Build a working Web OS from scratch. Terminal, apps, two games. Claude Code: 9:58, 80.3k tokens Agent Zero: 11:34, 59.7k tokens That's 26% fewer tokens for the same result. Full test at the end

Agent Zero

847,203 views • 3 months ago

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 views • 5 months 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

⚙️ AI Agents that build: Watch a .molt agent deploy a percolator program on a Seeker | Solana Mobile. Every OpenClaw instance comes with a built-in Solana development environment—zero setup, zero config. Just chat and deploy. Your agent doesn't just talk; it builds on-chain. 🦞🛠

⚙️ AI Agents that build: Watch a .molt agent deploy a percolator program on a Seeker | Solana Mobile. Every OpenClaw instance comes with a built-in Solana development environment—zero setup, zero config. Just chat and deploy. Your agent doesn't just talk; it builds on-chain. 🦞🛠

Molt.id

31,263 views • 7 months ago

i merged all my AI agents into one brain Claude Code, Codex, Gemini: one team, one memory, zero re-briefing result: 8+ hours a week back, and every agent already knows my projects, my clients and how i think here's the setup with Jarvix: 1. dump your context once: projects, clients, writing style, how you make decisions.. it builds your personal model from your actual AI interactions 2. switch agents mid-task with zero re-briefing: Claude Code builds, Codex reviews, Gemini researches, all reading the same context 3. it carries what YOU choose across sessions.. never start a chat from zero again 4. when it's time to act, it pulls the right agents together as one team instead of five separate assistants the unlock isn't another agent. it's that your context finally travels agents without shared memory are five interns on their first day, forever. agents with it are a team that's worked with you for years not more agents. one shared context that's the right bet P.S. thanks to the Jarvix team for the early access

i merged all my AI agents into one brain Claude Code, Codex, Gemini: one team, one memory, zero re-briefing result: 8+ hours a week back, and every agent already knows my projects, my clients and how i think here's the setup with Jarvix: 1. dump your context once: projects, clients, writing style, how you make decisions.. it builds your personal model from your actual AI interactions 2. switch agents mid-task with zero re-briefing: Claude Code builds, Codex reviews, Gemini researches, all reading the same context 3. it carries what YOU choose across sessions.. never start a chat from zero again 4. when it's time to act, it pulls the right agents together as one team instead of five separate assistants the unlock isn't another agent. it's that your context finally travels agents without shared memory are five interns on their first day, forever. agents with it are a team that's worked with you for years not more agents. one shared context that's the right bet P.S. thanks to the Jarvix team for the early access

Ronin

15,071 views • 2 months ago

I ran the same task on Claude Code and DeepSeek's new agent harness. One cost $150. The other cost $2. Today we're launching (AgentSky), the "OpenRouter for Agents" — one API → Claude Code, Codex, DeepSeek, Kimi, OpenCode, and every major agent in the cloud. And Agent Playground on top: race them on your own task, with your real tools (GitHub, Gmail, more), side by side in a browser: time, cost, tokens burnt. Guess which one was $2.

I ran the same task on Claude Code and DeepSeek's new agent harness. One cost $150. The other cost $2. Today we're launching (AgentSky), the "OpenRouter for Agents" — one API → Claude Code, Codex, DeepSeek, Kimi, OpenCode, and every major agent in the cloud. And Agent Playground on top: race them on your own task, with your real tools (GitHub, Gmail, more), side by side in a browser: time, cost, tokens burnt. Guess which one was $2.

Xiaoyin Qu

2,227,092 views • 2 months ago

Qwen3.8-Max became the brain of Atomic Agent, Hermes and OpenClaw. We gave the same task: Turn a photo of a hand-drawn floor plan into an interactive 3D walkthrough of that apartment and open it in the browser. Outputs: – Atomic Agent: 66 min, 557K tokens, $2.01 – OpenClaw: 32 min, 1.2M tokens, $1.12 – Hermes: 2 h 14 min, 4.2M tokens, $6.42 Before the start we leveled the field: one model endpoint, equal step and token budgets, equal timeouts, full autonomy, memory wiped on all three. Atomic Agent reads images through its vision tool, so it interrogated the sketch 14 times until every room, door and window turned into data. Then it drafted the whole scene in its head six times, threw away five drafts, and wrote the finished 19.8 KB file in one single write. After that it opened Chrome, checked its own render, and only then replied. The only agent of the three that verified its work, and the only one that stopped on its own. OpenClaw was twice as fast and the cheapest of the three, but its image tool kept timing out mid-run, and it shipped the palest apartment of the day: white rooms, no floor colors, one texture visibly glitched, and furniture you have to squint to find. It read the full plan three times, cut 11 room crops, wrote the scene in chunks, and landed the fastest and cheapest apartment of the day in 32 minutes. Then it kept polishing the finished file until we pulled the plug. Hermes worked the longest: two hours, 97 model calls, 4.2M tokens, and the apartment came out wrong anyway: doors standing loose in the middle of rooms, a 2 by 1.8 bath sprawled across a quarter of the flat, furniture drifting away from the plan. It measured everything twice and still built the least accurate apartment. Atomic Agent will run Qwen3.8-27B locally on day zero, next week!

Qwen3.8-Max became the brain of Atomic Agent, Hermes and OpenClaw. We gave the same task: Turn a photo of a hand-drawn floor plan into an interactive 3D walkthrough of that apartment and open it in the browser. Outputs: – Atomic Agent: 66 min, 557K tokens, $2.01 – OpenClaw: 32 min, 1.2M tokens, $1.12 – Hermes: 2 h 14 min, 4.2M tokens, $6.42 Before the start we leveled the field: one model endpoint, equal step and token budgets, equal timeouts, full autonomy, memory wiped on all three. Atomic Agent reads images through its vision tool, so it interrogated the sketch 14 times until every room, door and window turned into data. Then it drafted the whole scene in its head six times, threw away five drafts, and wrote the finished 19.8 KB file in one single write. After that it opened Chrome, checked its own render, and only then replied. The only agent of the three that verified its work, and the only one that stopped on its own. OpenClaw was twice as fast and the cheapest of the three, but its image tool kept timing out mid-run, and it shipped the palest apartment of the day: white rooms, no floor colors, one texture visibly glitched, and furniture you have to squint to find. It read the full plan three times, cut 11 room crops, wrote the scene in chunks, and landed the fastest and cheapest apartment of the day in 32 minutes. Then it kept polishing the finished file until we pulled the plug. Hermes worked the longest: two hours, 97 model calls, 4.2M tokens, and the apartment came out wrong anyway: doors standing loose in the middle of rooms, a 2 by 1.8 bath sprawled across a quarter of the flat, furniture drifting away from the plan. It measured everything twice and still built the least accurate apartment. Atomic Agent will run Qwen3.8-27B locally on day zero, next week!

Atomic Agent

123,376 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 • 28 days ago

Introducing Duet CLI. Now coding agents like Claude Code and Codex can call Duet (our agent-building agent) directly from the terminal to build and modify Decagon agents. Duet handles work within Decagon and returns the result while your coding agent stays focused on the broader task.

Introducing Duet CLI. Now coding agents like Claude Code and Codex can call Duet (our agent-building agent) directly from the terminal to build and modify Decagon agents. Duet handles work within Decagon and returns the result while your coding agent stays focused on the broader task.

Decagon

770,006 views • 2 months ago

This AI Agent made debugging 10x faster My website had a SERIOUS bug. So, I created 2 MiniMax Code CLI Agents: → BUG-FIXER Agent → FEATURE Agent Both Agents were working AT THE SAME TIME. Check the thread. NO code conflicts because both AI Agents were working on different GIT branches.

This AI Agent made debugging 10x faster My website had a SERIOUS bug. So, I created 2 MiniMax Code CLI Agents: → BUG-FIXER Agent → FEATURE Agent Both Agents were working AT THE SAME TIME. Check the thread. NO code conflicts because both AI Agents were working on different GIT branches.

Darshal Jaitwar

15,088 views • 1 month 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

Kylon launched a new chat app with AI agents like Codex or Claude being a part of the same team. Users on the same team can link an AI agent running on their own computer and let anyone on the team @ mention it in a thread to write code or sort files. > Agents can pass the next steps of a job to a coworker after finishing their part. > Apps can be built inside the conversation, like an invoice tracker, and published to their own web address. > Each agent can keep its own memory, with the team deciding which accounts it can use.

Kylon launched a new chat app with AI agents like Codex or Claude being a part of the same team. Users on the same team can link an AI agent running on their own computer and let anyone on the team @ mention it in a thread to write code or sort files. > Agents can pass the next steps of a job to a coworker after finishing their part. > Apps can be built inside the conversation, like an invoice tracker, and published to their own web address. > Each agent can keep its own memory, with the team deciding which accounts it can use.

🚨 AI News | TestingCatalog

276,828 views • 15 days ago

Introducing watchmen. It writes the skill files your coding agents should already have from your own sessions, shared across Claude Code, Codex, and pi, so you stop paying tokens to re-explain what your agent learned last week. Local and open-source.

Introducing watchmen. It writes the skill files your coding agents should already have from your own sessions, shared across Claude Code, Codex, and pi, so you stop paying tokens to re-explain what your agent learned last week. Local and open-source.

Dria

44,203 views • 5 months ago

OpenAI's new Agents API is a hosted Codex runtime that can connect to sandboxes like E2B. OpenAI manages the model, harness, and agent sessions, while code executes on an isolated E2B machine with its own filesystem and preinstalled tools. We built an agent workbench where each chat runs on its own machine. It starts from a custom template, auto-pauses between turns, forks to try another approach from the same starting point, and can even act on videos inside the sandbox. Thanks Ondrej for the workbench demo! Try it: e2b sbx create openai-agents-api-python-sdk Build on top of the workbench: Docs:

OpenAI's new Agents API is a hosted Codex runtime that can connect to sandboxes like E2B. OpenAI manages the model, harness, and agent sessions, while code executes on an isolated E2B machine with its own filesystem and preinstalled tools. We built an agent workbench where each chat runs on its own machine. It starts from a custom template, auto-pauses between turns, forks to try another approach from the same starting point, and can even act on videos inside the sandbox. Thanks Ondrej for the workbench demo! Try it: e2b sbx create openai-agents-api-python-sdk Build on top of the workbench: Docs:

Vasek Mlejnsky

23,210 views • 1 month ago

I rebuilt Posia using the Pi Agent SDK. The core agent is ~15 lines of code, and the harness is so flexible and hackable. Recorded a 17-min walkthrough on: - Pi’s extension system + how to build your own - extensions that cut tool tokens by 80–96% - the core Pi SDK, step by step - building hosted agents with it Adding my Pi extensions setup in AI Builder Club repo here:

I rebuilt Posia using the Pi Agent SDK. The core agent is ~15 lines of code, and the harness is so flexible and hackable. Recorded a 17-min walkthrough on: - Pi’s extension system + how to build your own - extensions that cut tool tokens by 80–96% - the core Pi SDK, step by step - building hosted agents with it Adding my Pi extensions setup in AI Builder Club repo here:

Jason Zhou

66,979 views • 3 months ago

Andrew Ng just dropped 1-hour course on full agent engineering with Claude Code: 1 prompt → agents team → graphs from 0% to 100%: 10% → 10:45 - build your first agent in Claude Code 20% → 16:24 - Graphs: Claude Code for subagents 55% → 33:15 - agent for grunt work on a cheaper model 80% → 43:58 - your first model, running locally 100% → 49:57 - fully local: zero cloud, zero bill the only course that takes you from Claude Code prompt to fully local agent - by Andrew Ng watch it today - then read how to build full graph system in the article below ↓

Andrew Ng just dropped 1-hour course on full agent engineering with Claude Code: 1 prompt → agents team → graphs from 0% to 100%: 10% → 10:45 - build your first agent in Claude Code 20% → 16:24 - Graphs: Claude Code for subagents 55% → 33:15 - agent for grunt work on a cheaper model 80% → 43:58 - your first model, running locally 100% → 49:57 - fully local: zero cloud, zero bill the only course that takes you from Claude Code prompt to fully local agent - by Andrew Ng watch it today - then read how to build full graph system in the article below ↓

codila

26,302 views • 2 months ago

If you use Cursor for coding, Claude Code for debugging, and local agents for automation, you almost certainly have a context problem. Every tool acts like an isolated employee. One assistant forgets what the other just learned. The biggest bottleneck in multi-agent workflows right now isn’t reasoning. It’s collective amnesia, combined with zero communication between agents. Memmy just launched a smart fix for this: a local, cross-agent memory layer. Instead of re-pasting your context everywhere, Memmy gives your stack a shared memory hub: → accumulate knowledge once, then use it across Cursor, Codex, and OpenClaw → automatically scan and import your existing agent history, so you don’t have to start from zero → keep your memory local, while model usage depends on your chosen provider or BYOK setup And it isn’t just a memory plugin. It’s a complete personal AI runtime with both MCP and a CLI. Memmy officially launched on Product Hunt, and the team is giving early users experiencing context fragmentation a free trial with 2M GPT tokens. Check it out and support the team with an upvote: → Best part? It’s also open-source for devs who want to build their own agents 🔥 Repo in 🧵↓

If you use Cursor for coding, Claude Code for debugging, and local agents for automation, you almost certainly have a context problem. Every tool acts like an isolated employee. One assistant forgets what the other just learned. The biggest bottleneck in multi-agent workflows right now isn’t reasoning. It’s collective amnesia, combined with zero communication between agents. Memmy just launched a smart fix for this: a local, cross-agent memory layer. Instead of re-pasting your context everywhere, Memmy gives your stack a shared memory hub: → accumulate knowledge once, then use it across Cursor, Codex, and OpenClaw → automatically scan and import your existing agent history, so you don’t have to start from zero → keep your memory local, while model usage depends on your chosen provider or BYOK setup And it isn’t just a memory plugin. It’s a complete personal AI runtime with both MCP and a CLI. Memmy officially launched on Product Hunt, and the team is giving early users experiencing context fragmentation a free trial with 2M GPT tokens. Check it out and support the team with an upvote: → Best part? It’s also open-source for devs who want to build their own agents 🔥 Repo in 🧵↓

Charly Wargnier

203,456 views • 3 months ago