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.

herdr 0.7.4 is out! many fixes, many additions, and structural work for multi-client 👀 but this one ships one of the two most wanted features: customizable sidebar. both agent and workspace rows: plugins, custom scripts, agent hooks, or just settings can put anything on them. claude's live task title,... show more

herdr

32,693 subscribers

94,840 views • 3 months ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

38 Comments

herdr3 months ago

and the second most wanted: floating panes (we named them popup panes in the architecture, so both names are correct :P). bind any script or command to a pane that floats over your layout lazygit, a scratch shell, or an agent hud that drills into whatever pane you're on. no splits harmed.

herdr3 months ago

also: sidebar rows no longer have a default gap between entries, so everything packs tighter and feels better. if you miss the old spacing, row_gap = 1 brings it back. row docs: full notes:

zebra3 months ago

It's amazing! Btw, your Pi status line is so cool. Would you mind sharing what plugin or configuration you're using for it?

herdr3 months ago

of course!

zebra3 months ago

Thank you!

Makaroni3 months ago

pac-man eating pi's context window is genuinely the most unhinged feature description ive ever read shipped it tho

Elijah Wilt3 months ago

Herdr is the best

Felipe Alves3 months ago

Herdr is the best

Ugur Tarlig3 months ago

Made Cmd+G in herdr open a “recent agents” picker: It jumps across Codex + Claude sessions, sorted by the latest real transcript event—not flaky file mtimes. Searchable, theme-aware, and Cmd+Shift+G keeps herdr’s native navigator. Code + tests:

Pres Mihaylov3 months ago

Excellent ship, was doing some workarounds in my fork to make this work, great to see it native

Pho3 months ago

Windows version when? I really love your windows builds

Crokily3 months ago

Just made a lazygit plugin for herdr: it starts as a compact sidebar for the Git stuff I use most, then expands into full lazygit with U when I need it. C opens an AI commit pane, and ; opens settings. been pretty handy for me so far Repo:

Vranac Srdjan3 months ago

that is awesome, thank you

Konrad Krasowski3 months ago

Fire 🔥. Thank you for the floating pane 🙏

Satyaa Goyal3 months ago

Bring that web server 😔

Tomas Varga3 months ago

Yes, thank you! i was just working on new plugin that can benefit from sidebar customizations.

Daniel3 months ago

w herdr 🙏

Fede3 months ago

Herdr is the GOAT.

Daniel White3 months ago

Goated 🐐🐐

Ugur Tarlig3 months ago

Thank you very much! With this release, are we able to have custom sorting in the sidebar? Recently active agents on top in the sidebar?

Synthetic Sea3 months ago

Herdr is so good, well done

Zinger Bee3 months ago

really cool

Eric Jeker3 months ago

Adopted!

Ray Todd3 months ago

What about the copy text issue which causes extra lines to be captured

Tosu of Black Wind 🌪️3 months ago

we like the sheep 🐑

Monty3 months ago

keep up the good work sir. thank u.

jintong.liu3 months ago

pretty cool!

BlockedPath3 months ago

Yes this is amazing!

ljudina833 months ago

is there a way to launch apps when starting herdr?

Raj Josyula3 months ago

Can we have @herdrdev integrated with @orca_build ?

Salem Sayed 🔻3 months ago

i need that pac-man

Nik3 months ago

really enjoying herdr thanks for all the hard work!

Bernhard Keprt3 months ago

Nice. Gonna check it out 👍

Spencer3 months ago

How is the PI configured in the Agents panel of the sidebar? I like it very much!

Waldo Milanes3 months ago

pac-man eating the context window started as a bit but that's genuinely the gauge i want most

Tài Ba Pi-Si3 months ago

Tôi không hiểu gì về Code hay về kỹ thuật. Những gì Bạn đang làm là đang đóng góp gì đó cho Pi Network đúng không?

pol3 months ago

Awesome! I’ve been using herdr inplace of tmux and it’s great. Although i have been having trouble with getting agents state on mac os running docker agent sandbox.

Sebastian Buzdugan3 months ago

custom sidebar is useful, but agent hooks need strict permission scopes before multi-client ships

Related Videos

Introducing the context course: a free course on doing ML with agent context. You will learn how to train models, optimize inferences, and build datasets, all by defining harness context with`SKILLS.md`, Plugins, MCP, Subagents, and Hooks. The course includes: - Weekly live AMA on YouTube - Weekly practical projects for ML with context - Instructions in Pi, Codex, Claude, and Opencode - Tutorials and guides on fundamentals - Interactive Quizzes Learn to give AI agents the right knowledge, tools, and structure to actually get work done. Skills, MCP servers, plugins, multi-agent workflows, and building an agent from scratch. Join here:

Introducing the context course: a free course on doing ML with agent context. You will learn how to train models, optimize inferences, and build datasets, all by defining harness context with`SKILLS.md`, Plugins, MCP, Subagents, and Hooks. The course includes: - Weekly live AMA on YouTube - Weekly practical projects for ML with context - Instructions in Pi, Codex, Claude, and Opencode - Tutorials and guides on fundamentals - Interactive Quizzes Learn to give AI agents the right knowledge, tools, and structure to actually get work done. Skills, MCP servers, plugins, multi-agent workflows, and building an agent from scratch. Join here:

Ben Burtenshaw

16,905 views • 6 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 • 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

26,500 views • 1 month ago

Opus 4.6 and Codex 5.3 just launched, so I did a hexagon test on both of them Opus 4.6 - 1M context - great for research + enterprise work - agent teams + long-range reasoning - weaker on raw code benchmarks Codex 5.3 - wins coding benchmarks - faster + mid-task steering - smaller context window TLDR: Opus = depth + orchestration Codex = speed + code

Opus 4.6 and Codex 5.3 just launched, so I did a hexagon test on both of them Opus 4.6 - 1M context - great for research + enterprise work - agent teams + long-range reasoning - weaker on raw code benchmarks Codex 5.3 - wins coding benchmarks - faster + mid-task steering - smaller context window TLDR: Opus = depth + orchestration Codex = speed + code

Abhinav

447,873 views • 9 months ago

Context V2 is live, the prediction market built for agents. Let your agent trade, build PM apps, and launch markets all through one API. Designed for the agentic economy.

Context V2 is live, the prediction market built for agents. Let your agent trade, build PM apps, and launch markets all through one API. Designed for the agentic economy.

Context

24,558 views • 7 months ago

Extensions now support Agent Skills and Hooks! 🛠️ Gemini CLI extensions let you bundle up: 🎓- Agent Skills 🪝- Hooks 🔌- MCP servers 📝- Context files 🧑‍💻- Custom commands Install one of the 300+ extensions that are live today or build your own.

Extensions now support Agent Skills and Hooks! 🛠️ Gemini CLI extensions let you bundle up: 🎓- Agent Skills 🪝- Hooks 🔌- MCP servers 📝- Context files 🧑‍💻- Custom commands Install one of the 300+ extensions that are live today or build your own.

Gemini CLI

170,286 views • 9 months ago

Compaction is death Repo Prompt turns deep orientation and planning into a single tool call, so your agent can ship complete features in one context window And when compaction does hit, Context Builder re-anchors them efficiently Big updates soon, but here's how it works today

Compaction is death Repo Prompt turns deep orientation and planning into a single tool call, so your agent can ship complete features in one context window And when compaction does hit, Context Builder re-anchors them efficiently Big updates soon, but here's how it works today

eric provencher

38,616 views • 9 months ago

Hit your usage limit in Codex/Claude Code mid-task? Orca now lets you resume the exact same session in a different agent harness — one click. Codex ⇄ Claude Code, full context intact🔥

Hit your usage limit in Codex/Claude Code mid-task? Orca now lets you resume the exact same session in a different agent harness — one click. Codex ⇄ Claude Code, full context intact🔥

Orca ADE

55,781 views • 3 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

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

Support for Agent Plugins is live in Cursor (and I made a plugin for searching X!) Agent Plugins combine Skills and MCP servers into a single package Think about them like an Ikea furniture kit: your table comes with instructions, parts, and tools. You use the instructions to understand how things work (which tools on which parts), then use the tools to assemble your furniture Agent Plugins are bundles of tools & resources that allow agents to accomplish a goal: - MCP servers: fixed context and tools - Skills: dynamic instructions, loaded progressively Plugins bundle tools and instructions so your agent is able to use tokens efficiently Many of us already use MCP servers and skills together - Agent Plugins formalize this pattern for more powerful workflows I'm excited to see where the standard takes us!

Support for Agent Plugins is live in Cursor (and I made a plugin for searching X!) Agent Plugins combine Skills and MCP servers into a single package Think about them like an Ikea furniture kit: your table comes with instructions, parts, and tools. You use the instructions to understand how things work (which tools on which parts), then use the tools to assemble your furniture Agent Plugins are bundles of tools & resources that allow agents to accomplish a goal: - MCP servers: fixed context and tools - Skills: dynamic instructions, loaded progressively Plugins bundle tools and instructions so your agent is able to use tokens efficiently Many of us already use MCP servers and skills together - Agent Plugins formalize this pattern for more powerful workflows I'm excited to see where the standard takes us!

matt palmer

40,935 views • 3 months ago

Last, but not least, don't sleep on this one: Le Chat now has Work mode (Preview) — a powerful agent for complex long-horizon tasks like research, analysis, and actions across your connected tools. Connectors are on by default so the agent pulls context from docs, email, and calendars as it works, and sessions persist across many turns until the task is complete.

Last, but not least, don't sleep on this one: Le Chat now has Work mode (Preview) — a powerful agent for complex long-horizon tasks like research, analysis, and actions across your connected tools. Connectors are on by default so the agent pulls context from docs, email, and calendars as it works, and sessions persist across many turns until the task is complete.

Vibe

34,302 views • 6 months ago

Everyone is building AI agents. Buda is building AI teams. Not one chatbot. Not one coding agent. A full workspace where multiple AI agents can collaborate, share context, access files, use tools, and execute real work together. Here’s what stood out 👇

Everyone is building AI agents. Buda is building AI teams. Not one chatbot. Not one coding agent. A full workspace where multiple AI agents can collaborate, share context, access files, use tools, and execute real work together. Here’s what stood out 👇

Pradeep Pandey

47,879 views • 5 months ago

Context-aware, action-ready. ChatGPT agent understands the task, chooses the right tool, and gets to work. It uses connectors, context, and custom instructions to take smarter actions on your behalf.

Context-aware, action-ready. ChatGPT agent understands the task, chooses the right tool, and gets to work. It uses connectors, context, and custom instructions to take smarter actions on your behalf.

OpenAI

143,301 views • 1 year ago

Codex now has plugins and CircleCI is in the directory. 🎉 The CircleCI plugin closes that loop by pulling pipeline context directly into your agent workflow so it can find failures, classify root causes, and verify fixes without leaving Codex. Find it here:

Codex now has plugins and CircleCI is in the directory. 🎉 The CircleCI plugin closes that loop by pulling pipeline context directly into your agent workflow so it can find failures, classify root causes, and verify fixes without leaving Codex. Find it here:

CircleCI

14,925 views • 6 months ago

On Day 3 of 12 Days of Agent Two: The Agent has eyes. Agent Two reads and understands ANYTHING you upload into the chat. Videos, images, scripts, PDFs, YouTube links, Drive files, brand books, rough cuts, whatever you give it. And it doesn't just read your files. It checks them against your project's context and understands what the uploaded video means and where it would be relevant and useful. Agent Two is frontier intelligence for creative work. 4x faster, at half the price.

Invideo

3,234,434 views • 3 months ago

CLM is one of the most elegant ideas we've worked on together. To me, it starts with a simple interaction need: there are many cases where I just want the agent to make surgical edits to the context. For example, when the agent finishes one task and prepares for another, it should ideally be able to clean up the context for the next one, just as a human would. And there are many such cases! Instead of hard-coding such rules into the harness (I doubt that's even possible), what would a first-principles solution to this problem look like? It turns out to be shockingly simple: ask the LLM to manage the context itself! Not only can this help the agent more efficiently solve the next task, but it can also be applied recursively to many more complex cases. This unlocks new agent capabilities across a variety of challenging, long-running, and open-ended tasks. For example, equipped with CLM, the agents can run continuously for hours on challenging tasks like EdgeBench or our new software world repository optimization tasks, and achieve really good results. Check out the CLM paper for more method details and many other cool results!

CLM is one of the most elegant ideas we've worked on together. To me, it starts with a simple interaction need: there are many cases where I just want the agent to make surgical edits to the context. For example, when the agent finishes one task and prepares for another, it should ideally be able to clean up the context for the next one, just as a human would. And there are many such cases! Instead of hard-coding such rules into the harness (I doubt that's even possible), what would a first-principles solution to this problem look like? It turns out to be shockingly simple: ask the LLM to manage the context itself! Not only can this help the agent more efficiently solve the next task, but it can also be applied recursively to many more complex cases. This unlocks new agent capabilities across a variety of challenging, long-running, and open-ended tasks. For example, equipped with CLM, the agents can run continuously for hours on challenging tasks like EdgeBench or our new software world repository optimization tasks, and achieve really good results. Check out the CLM paper for more method details and many other cool results!

Shannon Shen

15,797 views • 1 month ago

Introducing Nebula Live: The fastest way to work with your agents. You can now talk, text or show them anything. They work in real time, understand what you're saying and autonomously kick off work. Invite your teammates into a live session and everyone can collaborate together. Experience hands free building while just talking and the best part is all your context is saved in the workspace forever. Background mode mutes your agent but they still listen to you, kick off work and let you know when things are done. Share your screen or camera and your agent can see what you are doing. Now in beta across desktop, mobile and web. We're giving away $100 for you to experience Nebula Live. Reply with what you want to talk to your agents about.

Introducing Nebula Live: The fastest way to work with your agents. You can now talk, text or show them anything. They work in real time, understand what you're saying and autonomously kick off work. Invite your teammates into a live session and everyone can collaborate together. Experience hands free building while just talking and the best part is all your context is saved in the workspace forever. Background mode mutes your agent but they still listen to you, kick off work and let you know when things are done. Share your screen or camera and your agent can see what you are doing. Now in beta across desktop, mobile and web. We're giving away $100 for you to experience Nebula Live. Reply with what you want to talk to your agents about.

Nebula

11,761 views • 3 months ago

this is f*cking insane, that's what your agent looks like when it stops reading everything over and over Xerj launched Corpus Hub: 103 open-source knowledge corpora your agent can search instead of swallowing whole files the problem is simple, most agents dump entire documents into context just to find one paragraph you pay for every token, every single time with a corpus, the agent works differently: - it searches the corpus before opening anything - it pulls only the passages that answer the task - everything else stays out of the context window - it runs locally, so your files stay on your machine a bigger context window doesn't make an agent smarter, it just makes reading more expensive i gave my agent the same task with and without Xerj, here's the difference: > output tokens: 3× fewer > cost: $4.57 down to $1.98, 57% lower > tasks completed: 7/16 without Xerj, 16/16 with Xerj pick a corpus on connect it to your agent, then ask: "Work on this task using the connected corpus 1. Search the corpus before opening any full document 2. Pull only the passages you need and note where each one came from 3. If the corpus doesn't cover something, say so instead of guessing 4. At the end, list the passages you used and the files you never had to open" start with one corpus that matches your stack and one real task, then compare the token count before and after

this is f*cking insane, that's what your agent looks like when it stops reading everything over and over Xerj launched Corpus Hub: 103 open-source knowledge corpora your agent can search instead of swallowing whole files the problem is simple, most agents dump entire documents into context just to find one paragraph you pay for every token, every single time with a corpus, the agent works differently: - it searches the corpus before opening anything - it pulls only the passages that answer the task - everything else stays out of the context window - it runs locally, so your files stay on your machine a bigger context window doesn't make an agent smarter, it just makes reading more expensive i gave my agent the same task with and without Xerj, here's the difference: > output tokens: 3× fewer > cost: $4.57 down to $1.98, 57% lower > tasks completed: 7/16 without Xerj, 16/16 with Xerj pick a corpus on connect it to your agent, then ask: "Work on this task using the connected corpus 1. Search the corpus before opening any full document 2. Pull only the passages you need and note where each one came from 3. If the corpus doesn't cover something, say so instead of guessing 4. At the end, list the passages you used and the files you never had to open" start with one corpus that matches your stack and one real task, then compare the token count before and after

Anatoli Kopadze

18,791 views • 22 days ago