20+ Claude Code agents coordinating on real work (open source)
Single-agent LLMs suck at long-running complex tasks. We’ve open-sourced a multi-agent orchestrator that we’ve been using to handle long-running LLM tasks. We found that single LLM agents tend to stall, loop, or generate non-compiling code, so we built a harness for agents to coordinate over shared context while work is in progress. How it works: 1. Orchestrator agent that manages task decomposition 2. Sub-agents for parallel work 3. Subscriptions to task state and progress 4. Real-time sharing of intermediate discoveries between agents We tested this on a Putnam-level math problem, but the…
20+ Claude Code agents coordinating on real work (open source) launched on February 12, 2026 with 53 votes, #572 of 16,628 launches that month and more than 95% of that year's launches.
In plain words
This open-source multi-agent orchestrator enables Claude Code agents to coordinate on complex, long-running tasks by decomposing work across parallel sub-agents that share intermediate discoveries in real time. It addresses limitations of single-agent LLMs like stalling, looping, and non-compiling code generation. The system uses an orchestrator agent for task management, subscriptions to track progress, and shared context updates. Designed as a small, readable, and modifiable Claude Code skill, it has been tested on mathematical problems and generalizes to refactors, builds, and research tasks.
written from the facts on this page · September 2026
From the sources
Contribute to mutable-state-inc/lean-collab development by creating an account on GitHub.
Multi-agent collaborative theorem proving with Lean 4 and Ensue Memory Network. curl https://raw.githubusercontent.com/leanprover/elan/master/elan-init.sh -sSf | sh Restart your terminal or source the environment: lean --version lake --version Lean Project with Mathlib Your Lean project needs Mathlib. For a new project: lake build For existing projects, add to your lakefile.lean : require mathlib from git " https://github.com/leanprover-community/mathlib4 " Then run: curl --proto ' =https ' --tlsv1.2 -sSf https://sh.rustup.rs | sh Ensue API Key Get an API key from ensue.dev . git clone [email protected]:mutable-state-inc/lean-collab.git cd lean-collab-plugin make install This compiles the Rust…from github.com
In the maker’s words, at launch
Single-agent LLMs suck at long-running complex tasks. We’ve open-sourced a multi-agent orchestrator that we’ve been using to handle long-running LLM tasks. We found that single LLM agents tend to stall, loop, or generate non-compiling code, so we built a harness for agents to coordinate over shared context while work…
Does a similar job
all alternatives →
Agent OrchestratorAug 2026 · aoagents.dev · ▲56Run and supervise teams of coding agents from planning to merge. Any harness (Claude code, codex, +25 more). Desktop, web, mobile, and cloud agents. - Untrivial-ai/agent-orchestrator
OpenSwarm – Multi‑Agent Claude CLI Orchestrator for Linear/GitHubFeb 2026 · github.com · ▲34I built OpenSwarm because I wanted an autonomous “AI dev team” that can actually plug into my real workflow instead of running toy tasks. OpenSwarm orchestrates multiple Claude Code CLI instances as agents to work on real Linear issues. It: • pulls issues from Linear and runs a Worker/Reviewer/Test/Documenter pipeline • uses LanceDB + multilingual-e5 embeddings for long‑term memory and context reuse • builds a simple code knowledge graph for impact analysis • exposes everything through a Discord bot (status, dispatch, scheduling, logs) • can auto‑iterate on existing PRs and…
Give your coding agents the ability to message each otherNov 2025 · github.com · ▲14I finally got around to making a tool I've wanted for a long time: you can basically think of it as being "like Gmail for coding agents." If you've ever tried to use a bunch of instances of Claude Code or Codex at once across the same project, you've probably noticed how annoying it can be when they freak out about the other agent changing the files they're working on. Then they start doing annoying things, like restoring files from git, in the process wiping out another agent's work without a backup. Or if you've tried to have agents coordinate on two separate repos, like a Python backend…
- LLLessons learned from running Claude Code swarms at scaleJun 2026 · ▲10
Some time ago I built a simple app to run swarms of coding agents — I call it fleet (https://news.ycombinator.com/item?id=48256389). It's based on centralized beads with a Python orchestrator and can run any coder (Claude, agy, Codex). Recently I added a UI to manage the whole agent lifecycle: adding new tasks, monitoring running ones, and a chat interface built on MCP with a centralized SQLite DB. From the UI I can spawn agents to run in any directory, define dependencies on other tasks, and specify which coder/model should do the job. Today I can run 10–15 agents…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 28d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, February 2026
the whole month →
Lovon AI Therapy▲801Feel closer and have more fun with your partner every day!
AI · Feb 2026 · lovon.app
Hello my name is Ben Ward for the past 3 years I have been remastering the financial game Wall Street Raider created by Michael Jenkins originally on DOS in 1986. It has been a rough journey but I finally see the light at the end of the tunnel. I just recently redid the website and thought maybe the full story of how this project came to be would interest you all. Thank you for reading.
Work · Feb 2026 · wallstreetraider.com