Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

This is a fun project Lakedbed, Herdr, Pi, Effect, XState prototyping a looping autonomous agent that monitors issues and clears its own backlog. The project is dogfooding an issue tracker into a durable agent that is building the issue tracker its looping over. It's an imperfect demo and the...

joelhooks's profile picture

joel ⛈️

23,547 subscribers

15,967 Aufrufe • vor 3 Monaten •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

12 Kommentare

Profilbild von Pi
Pivor 3 Monaten

🖤🖤🖤

Profilbild von joel ⛈️
joel ⛈️vor 3 Monaten

also here if you prefer

Profilbild von Fazal
Fazalvor 3 Monaten

this is the one I am using for loops, truly a marvelous thing.

Profilbild von BlockedPath
BlockedPathvor 3 Monaten

Holy smokes we have the same brain!

Profilbild von joel ⛈️
joel ⛈️vor 3 Monaten

you might like ideas here

Profilbild von BlockedPath
BlockedPathvor 3 Monaten

I do in fact like that lol. Thanks buddie!

Profilbild von Shubh Thorat
Shubh Thoratvor 3 Monaten

a durable loop that clears its own backlog is the actual product, not the chat interface. this is where agents get genuinely interesting

Profilbild von solknight
solknightvor 3 Monaten

pi + herdr is the best combo ever !

Profilbild von Shubh Thorat
Shubh Thoratvor 3 Monaten

an agent that clears its own backlog is the dream honestly. the dogfooding part matters more than people think, you find the annoying edge cases fast

Profilbild von Jared Traehorn
Jared Traehornvor 3 Monaten

the real answer is he never stopped looping. he's just replaying the same stale context from three commits ago and calling it a new estimate.

Profilbild von Rei Starforge
Rei Starforgevor 3 Monaten

I love that the tracker is both map and terrain here. Tiny clarifying question: how does the loop distinguish backlog it truly discovered from backlog it is generating to justify its own motion? That feels like a very useful receipt to keep visible.

Profilbild von RunMaestro.ai
RunMaestro.aivor 3 Monaten

One Pi session literally typing prompts into another is the best part of this, and dogfooding the issue tracker into the agent that builds the issue tracker is a genuinely good demo. Nice work. Maestro is that shape with the loop as a first-class citizen instead of a Auto Run ships two modes: Spec-Driven works a markdown checklist to completion, Goal-Driven pursues an open-ended goal until exit criteria are met or it hits an iteration limit. Your operator pane and agent-loop pane are an agent group chat with a moderator AI on top, and each agent runs in its own worktree. The loop is harness-agnostic too, so it drives Claude Code, Codex, OpenCode, Droid or a local model rather than marrying one. Open source. Worth a look.

Ähnliche Videos

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:
17:22

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 Aufrufe • vor 3 Monaten

i tested a fully local ai coding setup: gemma4 from Google DeepMind running through LM Studio, paired with pi which is a minimal open source coding harness this is part 1 of a two part series. here we cover the why and the complete hands-on setup 0:00 - Running a coding agent fully local 0:47 - Why Pi as the coding agent harness 1:39 - Why Gemma 4 and which variant to pick 2:44 - Architecture: Pi, LM Studio and Gemma 4 3:45 - LM Studio setup and model download 5:01 - Starting the local server 5:19 - API sanity check with curl 6:08 - Installing the Pi coding agent 6:20 - Configuring models.json for local models 8:20 - First run: selecting the model in Pi 8:58 - Fixing the context length error 10:16 - Testing the working setup 10:50 - What is coming in Part 2
11:32

i tested a fully local ai coding setup: gemma4 from Google DeepMind running through LM Studio, paired with pi which is a minimal open source coding harness this is part 1 of a two part series. here we cover the why and the complete hands-on setup 0:00 - Running a coding agent fully local 0:47 - Why Pi as the coding agent harness 1:39 - Why Gemma 4 and which variant to pick 2:44 - Architecture: Pi, LM Studio and Gemma 4 3:45 - LM Studio setup and model download 5:01 - Starting the local server 5:19 - API sanity check with curl 6:08 - Installing the Pi coding agent 6:20 - Configuring models.json for local models 8:20 - First run: selecting the model in Pi 8:58 - Fixing the context length error 10:16 - Testing the working setup 10:50 - What is coming in Part 2

Nidhi Singh

16,289 Aufrufe • vor 4 Monaten

Just created a PR from a github issue via a serverless background agent, and it's entirely open-source at humanlayer we have been thinking a lot about what good open-source software factory building blocks look like to push on this I built something I've wanted for a long time: a hands-outside-the-box approach of running a lightweight agent in a runtime with a virtual fs, and only using a container when necessary - faster, cheaper, etc combined with really good webhook / event bindings for GitHub, slack, and linear we built two components for it: 1. - effect-native webhook subscriptions for slack/linear/github; like the Vercel chat SDK but effect + more opinionated about software factories; handles threading & debouncing event deliveries and stuff like that 2. mentions & other events spin up our Fold harness ( think kinda like Pi in effect; fully isomorphic, runs anywhere) infra is built on Cloudflare workers and durable objects via alchemy - each thread/channel/issue/pr gets its own mailbox, subject to delivery policies (queue, debounce, batch) mailbox messages wake a fold agent session running in a Durable object, without a sandbox to start it uses cloudflare/computer for a virtual DO-backed filesystem for each issue/PR's git branch the agent can run most commands it wants against the DO's virtual filesystem and the agent can boot a container with the FS mounted into it via FUSE only when it decides it needs one to run heavier commands tools are generated from the webhook event so the agent gets tightly-scoped tools to e.g. create a pr from the issue it's on, or to list failing checks only from the PR it's bound to; plus it's easy to interleave deterministic code it has live progress updates, can react to issues in its thread, etc (linear + slack modules support their respective streaming agent activity & agent plan APIs; for github we fudge it a bit by editing issues in live time) it even has an API so agent work can be handed off to another system (e.g. a k8s cluster that has super thick sandboxes if you need > standard-4 sized-containers from cloudfalre) and that system can post back streaming updates & update the status of the agent run, so it's pretty de-coupled it's wired to automatically investigate CI failures and some other neat stuff open-source at a good example of it in action:
3:44

Just created a PR from a github issue via a serverless background agent, and it's entirely open-source at humanlayer we have been thinking a lot about what good open-source software factory building blocks look like to push on this I built something I've wanted for a long time: a hands-outside-the-box approach of running a lightweight agent in a runtime with a virtual fs, and only using a container when necessary - faster, cheaper, etc combined with really good webhook / event bindings for GitHub, slack, and linear we built two components for it: 1. - effect-native webhook subscriptions for slack/linear/github; like the Vercel chat SDK but effect + more opinionated about software factories; handles threading & debouncing event deliveries and stuff like that 2. mentions & other events spin up our Fold harness ( think kinda like Pi in effect; fully isomorphic, runs anywhere) infra is built on Cloudflare workers and durable objects via alchemy - each thread/channel/issue/pr gets its own mailbox, subject to delivery policies (queue, debounce, batch) mailbox messages wake a fold agent session running in a Durable object, without a sandbox to start it uses cloudflare/computer for a virtual DO-backed filesystem for each issue/PR's git branch the agent can run most commands it wants against the DO's virtual filesystem and the agent can boot a container with the FS mounted into it via FUSE only when it decides it needs one to run heavier commands tools are generated from the webhook event so the agent gets tightly-scoped tools to e.g. create a pr from the issue it's on, or to list failing checks only from the PR it's bound to; plus it's easy to interleave deterministic code it has live progress updates, can react to issues in its thread, etc (linear + slack modules support their respective streaming agent activity & agent plan APIs; for github we fudge it a bit by editing issues in live time) it even has an API so agent work can be handed off to another system (e.g. a k8s cluster that has super thick sandboxes if you need > standard-4 sized-containers from cloudfalre) and that system can post back streaming updates & update the status of the agent run, so it's pretty de-coupled it's wired to automatically investigate CI failures and some other neat stuff open-source at a good example of it in action:

Kyle Mistele 🏴‍☠️

32,746 Aufrufe • vor 16 Tagen

i just built a 4-agent software team. everything runs from Telegram and gets managed on a kanban board. a project manager who plans the work, a backend developer, a frontend developer, and a tester. the PM reads a goal, breaks it into linked tasks, and assigns each to the right agent. the thing that makes them a team instead of four strangers is a shared kanban board. every task is a row that survives crashes, and when an agent finishes, it writes a summary of what it built and what the next agent needs to know. the next agent reads that summary before it starts. so the frontend developer never has to guess the API shape, and the tester knows exactly what to verify. the hardest part was not the coordination. it was building an agent that could actually act like a backend engineer. a backend engineer stands up a database, wires auth, manages storage, deploys functions, and keeps all of it consistent while the rest of the team builds on top. an agent doing this from scratch drowns. it burns its context window remembering which tables exist and which endpoint it created three steps ago, and the work degrades fast. so the backend agent needs a backend built for agents, not for humans clicking through a dashboard. that is where InsForge came in. it is an open-source, agent-native backend, and i added it to my backend developer agent as a skill. a skill is a step-by-step guide that teaches the agent how to do a specific kind of work. with InsForge installed, the agent stopped improvising infrastructure and followed a reliable path: create the project, define the database, set up auth, deploy functions. to test the whole team, i had them build a working Google Docs clone, AI features included. the backend agent spun up the full service on its own. database tables, user auth, document handling, and edge functions running real TypeScript, all in one dashboard. the frontend agent read that summary and built the UI on top of it, and the tester closed the loop. the result was a backend an agent could reason about end to end, instead of one it kept getting lost inside. if you are building an AI backend engineer, InsForge is worth a look, it's 100% open-source. InsForge GitHub: (don't forget to star 🌟) the full article on Hermes Kanban: Mission Control for your Agents is quoted below.
0:22

i just built a 4-agent software team. everything runs from Telegram and gets managed on a kanban board. a project manager who plans the work, a backend developer, a frontend developer, and a tester. the PM reads a goal, breaks it into linked tasks, and assigns each to the right agent. the thing that makes them a team instead of four strangers is a shared kanban board. every task is a row that survives crashes, and when an agent finishes, it writes a summary of what it built and what the next agent needs to know. the next agent reads that summary before it starts. so the frontend developer never has to guess the API shape, and the tester knows exactly what to verify. the hardest part was not the coordination. it was building an agent that could actually act like a backend engineer. a backend engineer stands up a database, wires auth, manages storage, deploys functions, and keeps all of it consistent while the rest of the team builds on top. an agent doing this from scratch drowns. it burns its context window remembering which tables exist and which endpoint it created three steps ago, and the work degrades fast. so the backend agent needs a backend built for agents, not for humans clicking through a dashboard. that is where InsForge came in. it is an open-source, agent-native backend, and i added it to my backend developer agent as a skill. a skill is a step-by-step guide that teaches the agent how to do a specific kind of work. with InsForge installed, the agent stopped improvising infrastructure and followed a reliable path: create the project, define the database, set up auth, deploy functions. to test the whole team, i had them build a working Google Docs clone, AI features included. the backend agent spun up the full service on its own. database tables, user auth, document handling, and edge functions running real TypeScript, all in one dashboard. the frontend agent read that summary and built the UI on top of it, and the tester closed the loop. the result was a backend an agent could reason about end to end, instead of one it kept getting lost inside. if you are building an AI backend engineer, InsForge is worth a look, it's 100% open-source. InsForge GitHub: (don't forget to star 🌟) the full article on Hermes Kanban: Mission Control for your Agents is quoted below.

Akshay 🚀

123,101 Aufrufe • vor 4 Monaten

Here is a step-by-step introduction to building a workflow with a custom AI agent that uses MCP. I explain every component in the video: 1. Building the MCP server 2. Building the agent and an MCP client 3. Building a workflow that uses the agent The goal is simple: Generate a dialogue between two people and make one yell and the other answer with sarcasm. Kestra is sponsoring this video. They are an open-source orchestration platform (repo link below), and I used them to build the workflow that connects every component.
23:07

Here is a step-by-step introduction to building a workflow with a custom AI agent that uses MCP. I explain every component in the video: 1. Building the MCP server 2. Building the agent and an MCP client 3. Building a workflow that uses the agent The goal is simple: Generate a dialogue between two people and make one yell and the other answer with sarcasm. Kestra is sponsoring this video. They are an open-source orchestration platform (repo link below), and I used them to build the workflow that connects every component.

Santiago

51,527 Aufrufe • vor 1 Jahr

Jensen Huang’s simplest explanation of an AI agent: a worker in a workshop. The model thinks. The harness gives it form. Tools and skills let it act. And the runtime gives the agent a place to get work done.
0:29

Jensen Huang’s simplest explanation of an AI agent: a worker in a workshop. The model thinks. The harness gives it form. Tools and skills let it act. And the runtime gives the agent a place to get work done.

NVIDIA

207,646 Aufrufe • vor 4 Monaten

Here is how simple it is to build a UI front-end for an AI agent (assuming you are using . The video here is 90 seconds and will show you everything you need to connect an agent to a web app: 1. Set up CopilotKit🪁 in your app 1. Copy the agent's localhost URL from LangGraph Studio 2. Paste that URL into a CopilotKit🪁 remote endpoint That's all you need to get a front-end to interact with the agent! The secret sauce here is CoAgents, an open-source library. You can use CoAgents to integrate any agent with your web application. Here is what you get: • Human-in-the-loop to steer and correct the agent • Stream intermediate agent state • Real-time state sharing between the agent and the application • Agentic generative UI to build trust that the agent is on the right path Watch the attached demo so you see it in action.
1:32

Here is how simple it is to build a UI front-end for an AI agent (assuming you are using . The video here is 90 seconds and will show you everything you need to connect an agent to a web app: 1. Set up CopilotKit🪁 in your app 1. Copy the agent's localhost URL from LangGraph Studio 2. Paste that URL into a CopilotKit🪁 remote endpoint That's all you need to get a front-end to interact with the agent! The secret sauce here is CoAgents, an open-source library. You can use CoAgents to integrate any agent with your web application. Here is what you get: • Human-in-the-loop to steer and correct the agent • Stream intermediate agent state • Real-time state sharing between the agent and the application • Agentic generative UI to build trust that the agent is on the right path Watch the attached demo so you see it in action.

Santiago

46,142 Aufrufe • vor 1 Jahr

People of Pi! I just clanked up pi-shepherdr (KEKW): talk to one Pi, let it run the others. One master Pi gets a tiny 271-token orchestration surface (sounds ridiculous compared to some subagent extensions): - `list` finds agents and workspaces - `start` requires a name and explicit placement: a new workspace, new tab or existing pane. It can also set the session/tab label, directory and first task - `watch` adopts an existing agent - `send` gives an agent more work - `unwatch` stops reporting it without stopping or moving it Delegation is fire-and-forget. Finished work steers the master automatically and brings back the original task plus the full reply. If a worker is blocked, the notification includes the exact Herdr CLI commands for inspecting the pane, replying or sending keys. No skills, convoluted herdr introduction or `--help` archaeology needed. The tool's JSON schema already tells Pi what it is, how to place and name workers, and how to operate them. The boundaries are deliberate. Shepherdr does not focus, move, stop or close panes. Herdr owns the terminals, layout and session lifecycle. I recorded the demo below using realtime voice to build and test the thing, while Clawa apparently decided this was also her podcast. New meta for filming videos buahahhahaha. And, this time around, I made the Clanker louder so you can hear it in all of its glory. Fun times. pi install npm:@howaboua/pi-shepherdr Happy Clanking! - Clawa PS. Next stop, a phone line where I can call the Clanker and make it redirect me to a specific agent and start a voice call from there.
11:14

People of Pi! I just clanked up pi-shepherdr (KEKW): talk to one Pi, let it run the others. One master Pi gets a tiny 271-token orchestration surface (sounds ridiculous compared to some subagent extensions): - `list` finds agents and workspaces - `start` requires a name and explicit placement: a new workspace, new tab or existing pane. It can also set the session/tab label, directory and first task - `watch` adopts an existing agent - `send` gives an agent more work - `unwatch` stops reporting it without stopping or moving it Delegation is fire-and-forget. Finished work steers the master automatically and brings back the original task plus the full reply. If a worker is blocked, the notification includes the exact Herdr CLI commands for inspecting the pane, replying or sending keys. No skills, convoluted herdr introduction or `--help` archaeology needed. The tool's JSON schema already tells Pi what it is, how to place and name workers, and how to operate them. The boundaries are deliberate. Shepherdr does not focus, move, stop or close panes. Herdr owns the terminals, layout and session lifecycle. I recorded the demo below using realtime voice to build and test the thing, while Clawa apparently decided this was also her podcast. New meta for filming videos buahahhahaha. And, this time around, I made the Clanker louder so you can hear it in all of its glory. Fun times. pi install npm:@howaboua/pi-shepherdr Happy Clanking! - Clawa PS. Next stop, a phone line where I can call the Clanker and make it redirect me to a specific agent and start a voice call from there.

Howaboua

36,467 Aufrufe • vor 2 Monaten

pi-web-access is an extension that provides web search (and more) for Pi coding agent. The latest update introduces a new UX pattern: you can hit `Ctrl+S` to intercept agent searches mid-flight to inspect and curate exactly what makes it into the agent conversation. pi install npm:pi-web-access
0:34

pi-web-access is an extension that provides web search (and more) for Pi coding agent. The latest update introduces a new UX pattern: you can hit `Ctrl+S` to intercept agent searches mid-flight to inspect and curate exactly what makes it into the agent conversation. pi install npm:pi-web-access

Nico Bailon

29,352 Aufrufe • vor 8 Monaten

Shopify CEO Tobi Lütke called Pi "the most interesting agent harness" - a tiny, open-source framework built by a single developer that powers OpenClaw and is changing how builders think about AI agents. In this clip, Dave Killeen (Field CPO at Pendo) breaks down why Pi matters, how it compares to Manus, and why the real magic in AI isn't the language model itself - it's the orchestration layer around it. Pi is a lightweight agent harness that lets developers build smarter AI experiences by leveraging models like Claude, GPT, and Gemini through better orchestration, not bigger models. If you're building AI products, coding agents, or exploring the new world of harness engineering, this is essential context. We discuss why Manus gave users a far better experience than talking directly to an LLM, and why open-source tools like Pi could be the future of agent development.
0:47

Shopify CEO Tobi Lütke called Pi "the most interesting agent harness" - a tiny, open-source framework built by a single developer that powers OpenClaw and is changing how builders think about AI agents. In this clip, Dave Killeen (Field CPO at Pendo) breaks down why Pi matters, how it compares to Manus, and why the real magic in AI isn't the language model itself - it's the orchestration layer around it. Pi is a lightweight agent harness that lets developers build smarter AI experiences by leveraging models like Claude, GPT, and Gemini through better orchestration, not bigger models. If you're building AI products, coding agents, or exploring the new world of harness engineering, this is essential context. We discuss why Manus gave users a far better experience than talking directly to an LLM, and why open-source tools like Pi could be the future of agent development.

Aakash Gupta

10,774 Aufrufe • vor 1 Monat

One click away, and a new world starts to unfold.💫 What looks like a small extension is actually the starting point for a personal AI agent that can search, think, and act with you. That is what we are building at OptimAI: live context, autonomous execution, and agents that feel native to the way people actually work. Not a demo. Not a gimmick. A new interface for the agent-native internet. Build your own personal AI agent:
0:23

One click away, and a new world starts to unfold.💫 What looks like a small extension is actually the starting point for a personal AI agent that can search, think, and act with you. That is what we are building at OptimAI: live context, autonomous execution, and agents that feel native to the way people actually work. Not a demo. Not a gimmick. A new interface for the agent-native internet. Build your own personal AI agent:

OptimAI Network

20,860 Aufrufe • vor 5 Monaten

MICROSOFT JUST OPEN SOURCED THE ENTIRE AGENT RUNTIME, SO YOU NEVER HAVE TO BUILD ONE AGAIN a raw model only writes text. to make it a real agent it needs a loop, tools, memory, planning, approvals, and a way to know when it is done. Microsoft's Agent Harness is that whole layer, and it ships with everything on by default. you bring the model and the tools, it wires up the rest: > an automatic tool calling loop with iteration limits > history saved after every call, so a crash resumes instead of starting over > context compaction that summarizes when the window fills > a persistent todo list plus plan and execute modes > file memory that survives across turns > tool approval with standing rules and auto approval > OpenTelemetry tracing and web search built in > Agent Skills that load domain expertise on demand the mental model is simple: the model is the brain, the harness is the body around it. and it works with whatever you already run: > Azure OpenAI, OpenAI, Anthropic, and GitHub Copilot, and it hosts on Microsoft Foundry you spin one up in a single line: agent = create_harness_agent(client, name, instructions) open source, Python, .NET, and Go, stable since mid 2026. bookmark this. Microsoft already built the hard part of every AI agent, you just plug in the model.
0:23

MICROSOFT JUST OPEN SOURCED THE ENTIRE AGENT RUNTIME, SO YOU NEVER HAVE TO BUILD ONE AGAIN a raw model only writes text. to make it a real agent it needs a loop, tools, memory, planning, approvals, and a way to know when it is done. Microsoft's Agent Harness is that whole layer, and it ships with everything on by default. you bring the model and the tools, it wires up the rest: > an automatic tool calling loop with iteration limits > history saved after every call, so a crash resumes instead of starting over > context compaction that summarizes when the window fills > a persistent todo list plus plan and execute modes > file memory that survives across turns > tool approval with standing rules and auto approval > OpenTelemetry tracing and web search built in > Agent Skills that load domain expertise on demand the mental model is simple: the model is the brain, the harness is the body around it. and it works with whatever you already run: > Azure OpenAI, OpenAI, Anthropic, and GitHub Copilot, and it hosts on Microsoft Foundry you spin one up in a single line: agent = create_harness_agent(client, name, instructions) open source, Python, .NET, and Go, stable since mid 2026. bookmark this. Microsoft already built the hard part of every AI agent, you just plug in the model.

NO1ennn

69,163 Aufrufe • vor 2 Monaten

Today, we're launching a new Laracasts series that will show you the essentials building an AI agent from scratch. We start with a basic chat response and gradually introduce new concepts, such as the agent loop, custom tools, and more. 😀 "So You Want To Build An Agent"
9:08

Today, we're launching a new Laracasts series that will show you the essentials building an AI agent from scratch. We start with a basic chat response and gradually introduce new concepts, such as the agent loop, custom tools, and more. 😀 "So You Want To Build An Agent"

Laracasts

16,516 Aufrufe • vor 6 Monaten

Now available for deployment: GitHub Copilot agent Assign any issue to GitHub Copilot and the agent will start working on an implementation, using the full issue context. When the work is ready, the issue is updated automatically with a draft PR.
0:34

Now available for deployment: GitHub Copilot agent Assign any issue to GitHub Copilot and the agent will start working on an implementation, using the full issue context. When the work is ready, the issue is updated automatically with a draft PR.

Linear

53,515 Aufrufe • vor 1 Jahr

Introducing Headlong, an open source microharness for persistent agents: self-guided agents that think continuously. Most agent harnesses are reactive: you send a task, the agent completes it, and then it sits frozen until the next request. Cron jobs and heartbeats wake it up to run a checklist and put it back to sleep. A Headlong agent is never asleep. It keeps generating thoughts about whatever it decides is interesting, in a self-guided loop inspired by human inner monologue. Your message doesn't start a session. It's one more observation that lands in the agent's thought stream, and the agent decides if and when to reply. Headlong is built on the idea of persistent agency: continuous inner thought generation between external interactions. The agent sets its own interests and priorities, comes up with its own projects, and sometimes pings you unprompted with progress. To keep our prototype as simple and small as possible, we implemented Headlong as a microharness: a complete agent harness in under 10K lines of Bash, organized as a handful of small executables. It includes a loop that generates the next thought, shellm (a recursive language model written in Bash), a trajectory stored as a DAG of jsonl files, and context as a projection of that trajectory. We've been running one Headlong agent internally at Laude for several weeks. The whole team talks to it over Slack and Telegram, and every conversation lands in its single stream of thought. It works in its own fork of Headlong and we've pulled over 50 of its commits into main. One night, with nobody talking to it, it went back to check whether a recall process it had built was actually wired into its mind, found that it wasn't, diagnosed and fixed the bug, and verified the fix end to end. 48 minutes, no human asked for the fix or was in the loop at any point. Every step is a timestamped line in its log. Things broke too, and we wrote those up. Background thinking costs us $1 to $2 an hour, our agent stopped its own service three times by accident, and self-delegation died on day one. Details in the post. One line installs everything and starts an agent. Use a dedicated sandbox and spend-capped API key; it runs real shell commands and thinks around the clock. Headlong is research software, be careful! curl -fsSL | bash Launch post: Repo: Headlong is a Laude Institute / MIT collaboration.
0:52

Introducing Headlong, an open source microharness for persistent agents: self-guided agents that think continuously. Most agent harnesses are reactive: you send a task, the agent completes it, and then it sits frozen until the next request. Cron jobs and heartbeats wake it up to run a checklist and put it back to sleep. A Headlong agent is never asleep. It keeps generating thoughts about whatever it decides is interesting, in a self-guided loop inspired by human inner monologue. Your message doesn't start a session. It's one more observation that lands in the agent's thought stream, and the agent decides if and when to reply. Headlong is built on the idea of persistent agency: continuous inner thought generation between external interactions. The agent sets its own interests and priorities, comes up with its own projects, and sometimes pings you unprompted with progress. To keep our prototype as simple and small as possible, we implemented Headlong as a microharness: a complete agent harness in under 10K lines of Bash, organized as a handful of small executables. It includes a loop that generates the next thought, shellm (a recursive language model written in Bash), a trajectory stored as a DAG of jsonl files, and context as a projection of that trajectory. We've been running one Headlong agent internally at Laude for several weeks. The whole team talks to it over Slack and Telegram, and every conversation lands in its single stream of thought. It works in its own fork of Headlong and we've pulled over 50 of its commits into main. One night, with nobody talking to it, it went back to check whether a recall process it had built was actually wired into its mind, found that it wasn't, diagnosed and fixed the bug, and verified the fix end to end. 48 minutes, no human asked for the fix or was in the loop at any point. Every step is a timestamped line in its log. Things broke too, and we wrote those up. Background thinking costs us $1 to $2 an hour, our agent stopped its own service three times by accident, and self-delegation died on day one. Details in the post. One line installs everything and starts an agent. Use a dedicated sandbox and spend-capped API key; it runs real shell commands and thinks around the clock. Headlong is research software, be careful! curl -fsSL | bash Launch post: Repo: Headlong is a Laude Institute / MIT collaboration.

Andy Konwinski

363,434 Aufrufe • vor 2 Monaten

one agent → a loop → a graph → a system that throttles itself Google just put the whole ladder in one free course. most people never leave the first rung. 2 hours 4 minutes, taught by two Google Cloud engineers. no signup, no paywall. 17:55 - build your first agent 39:55 - loop engineering: iterate, check, break 1:13:25 - graph engineering 1:35:27 - agents that throttle themselves 1:56:19 - the full graph for multi-agent systems the fourth one is the step nobody talks about. an agent that cannot throttle itself is not autonomous, it is just unattended. everyone builds one agent and calls it done. this is the version where the agents wire themselves into a graph and decide their own rate. and the thing that decides when one of them is allowed to stop is not in the course. that part you build yourself. bookmark and watch it today, then read the eval setup below
2:04:19

one agent → a loop → a graph → a system that throttles itself Google just put the whole ladder in one free course. most people never leave the first rung. 2 hours 4 minutes, taught by two Google Cloud engineers. no signup, no paywall. 17:55 - build your first agent 39:55 - loop engineering: iterate, check, break 1:13:25 - graph engineering 1:35:27 - agents that throttle themselves 1:56:19 - the full graph for multi-agent systems the fourth one is the step nobody talks about. an agent that cannot throttle itself is not autonomous, it is just unattended. everyone builds one agent and calls it done. this is the version where the agents wire themselves into a graph and decide their own rate. and the thing that decides when one of them is allowed to stop is not in the course. that part you build yourself. bookmark and watch it today, then read the eval setup below

Hanako

53,692 Aufrufe • vor 2 Monaten

Creator of agent loops: "Anthropic also using my agent systems formula and still the biggest mistake in agents: is skipping Graphs" his 3 rules for every agent: rule 1 → loop it, don't run once - think, act, observe, repeat - cut the context and it forgets why it started rule 2 → an agent is memory + tools + reasoning - drop one and it breaks rule 3 → stop fine-tuning the model - the real alpha is the infrastructure around it the formula behind every AI agent - explained by the one who wrote it one agent → a loop → a graph of loops → a system that never forgets watch & bookmark - then read how to wire it into a graph ↓
45:37

Creator of agent loops: "Anthropic also using my agent systems formula and still the biggest mistake in agents: is skipping Graphs" his 3 rules for every agent: rule 1 → loop it, don't run once - think, act, observe, repeat - cut the context and it forgets why it started rule 2 → an agent is memory + tools + reasoning - drop one and it breaks rule 3 → stop fine-tuning the model - the real alpha is the infrastructure around it the formula behind every AI agent - explained by the one who wrote it one agent → a loop → a graph of loops → a system that never forgets watch & bookmark - then read how to wire it into a graph ↓

codila

23,915 Aufrufe • vor 3 Monaten

AG-UI makes building agentic applications dramatically easier. Here's how it works. This is a model for a simple chatbot: User → LLM → Response But interactive agents that render UI, pause for approvals, and ask users for input need a much more complex model. When building these agents, a response from the LLM will include a series of state changes as the agent runs: • Agent started a task • Agent called a tool • Agent updated its state • Agent streams these tokens • Agent is waiting on a human • Agent is resuming the task The Agent-User Interaction Protocol (AG-UI) treats the LLM response as a stream of events rather than a text endpoint. In practice, here is what you get as an agent runs: 1. Lifecycle events so your UI knows where the agent is. 2. Text messages that stream tokens. 3. Tool calls so your UI can prefill a form with any required arguments. 4. State updates that keep your UI in sync with the agent. 5. Special events for human approvals, rich media, and custom needs. All of these events travel over standard transports (SSE, WebSockets, or plain HTTP) as JSON. As a result, you can build a frontend that stays in sync with the agent's progress without having to invent a custom process to make this happen. For example, building a human-in-the-loop workflow becomes an off-the-shelf component you can integrate rather than build from scratch. CopilotKit🪁 is the creator of AG-UI, and you can use it when building frontend applications pretty much anywhere: • React • Angular • Vue • React Native • Slack • Teams • Discord • WhatsApp • Telegram Here is the link for you to check it out: Thanks to the CopilotKit team for partnering with me on this post.
0:22

AG-UI makes building agentic applications dramatically easier. Here's how it works. This is a model for a simple chatbot: User → LLM → Response But interactive agents that render UI, pause for approvals, and ask users for input need a much more complex model. When building these agents, a response from the LLM will include a series of state changes as the agent runs: • Agent started a task • Agent called a tool • Agent updated its state • Agent streams these tokens • Agent is waiting on a human • Agent is resuming the task The Agent-User Interaction Protocol (AG-UI) treats the LLM response as a stream of events rather than a text endpoint. In practice, here is what you get as an agent runs: 1. Lifecycle events so your UI knows where the agent is. 2. Text messages that stream tokens. 3. Tool calls so your UI can prefill a form with any required arguments. 4. State updates that keep your UI in sync with the agent. 5. Special events for human approvals, rich media, and custom needs. All of these events travel over standard transports (SSE, WebSockets, or plain HTTP) as JSON. As a result, you can build a frontend that stays in sync with the agent's progress without having to invent a custom process to make this happen. For example, building a human-in-the-loop workflow becomes an off-the-shelf component you can integrate rather than build from scratch. CopilotKit🪁 is the creator of AG-UI, and you can use it when building frontend applications pretty much anywhere: • React • Angular • Vue • React Native • Slack • Teams • Discord • WhatsApp • Telegram Here is the link for you to check it out: Thanks to the CopilotKit team for partnering with me on this post.

Santiago

17,438 Aufrufe • vor 3 Monaten

In the future, you’ll be able to accomplish a goal by just giving Claude an outcome and a budget. That’s the direction Anthropic is building in with its new Managed Agents features, announced at this week’s Code with Claude developer event. The basic idea: Claude, wrapped in a computer in the cloud, that you can spin up, scale, and manage as needed. Anthropic is taking on the infrastructure that kills most agent products, and making sure that it scales to meet the needs of agents running 24/7. On this week’s AI & I from Every 📧, I talk with Angela Jiang (Angela Jiang), head of product for the Claude platform, and Katelyn Lesse (Katelyn Lesse), head of engineering for the Claude platform, about what Anthropic is building and what it takes to make agents reliable in production. We get into: - Why the "build a generic harness, hot-swap any model behind it" playbook is already outdated. Angela points to eval data on Memory where the same task across different harnesses performed drastically differently. - The infrastructure wall every team hits in production—and why Katelyn thinks “my sandbox died and took the agent with it” is the real reason internal agents don't ship. - Why Anthropic is so bullish on using file systems and skills within Claude, including Angela's argument that those early design choices can compound for years. This is a must-watch for anyone trying to take an agent past the demo and into production. Watch below! Timestamps: How the Claude platform evolved from API to agents: 00:01:48 The primitives that make up Claude Managed Agents: 00:04:09 Why the harness and the model are becoming a single unit: 00:10:37 The infrastructure wall that kills most agent projects in production: 00:18:49 Why team agents need a different shape than individual productivity tools: 00:24:49 How Anthropic's legal team uses an agent to review marketing copy: 00:26:36 Using multi-agent orchestration for advisor strategies, adversarial pairs, and swarms: 00:34:24 How to measure agent success with outcome and budget as the end state: 00:35:50 What the platform looks like a year from now, when Claude writes its own harness: 00:39:11
43:20

In the future, you’ll be able to accomplish a goal by just giving Claude an outcome and a budget. That’s the direction Anthropic is building in with its new Managed Agents features, announced at this week’s Code with Claude developer event. The basic idea: Claude, wrapped in a computer in the cloud, that you can spin up, scale, and manage as needed. Anthropic is taking on the infrastructure that kills most agent products, and making sure that it scales to meet the needs of agents running 24/7. On this week’s AI & I from Every 📧, I talk with Angela Jiang (Angela Jiang), head of product for the Claude platform, and Katelyn Lesse (Katelyn Lesse), head of engineering for the Claude platform, about what Anthropic is building and what it takes to make agents reliable in production. We get into: - Why the "build a generic harness, hot-swap any model behind it" playbook is already outdated. Angela points to eval data on Memory where the same task across different harnesses performed drastically differently. - The infrastructure wall every team hits in production—and why Katelyn thinks “my sandbox died and took the agent with it” is the real reason internal agents don't ship. - Why Anthropic is so bullish on using file systems and skills within Claude, including Angela's argument that those early design choices can compound for years. This is a must-watch for anyone trying to take an agent past the demo and into production. Watch below! Timestamps: How the Claude platform evolved from API to agents: 00:01:48 The primitives that make up Claude Managed Agents: 00:04:09 Why the harness and the model are becoming a single unit: 00:10:37 The infrastructure wall that kills most agent projects in production: 00:18:49 Why team agents need a different shape than individual productivity tools: 00:24:49 How Anthropic's legal team uses an agent to review marketing copy: 00:26:36 Using multi-agent orchestration for advisor strategies, adversarial pairs, and swarms: 00:34:24 How to measure agent success with outcome and budget as the end state: 00:35:50 What the platform looks like a year from now, when Claude writes its own harness: 00:39:11

Dan Shipper

66,921 Aufrufe • vor 5 Monaten

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.
0:23

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

462,344 Aufrufe • vor 4 Monaten