Sign inLaunch

Open-source AI agents

Open-source AI agents launched on AI Launch, ranked by community upvotes. 12 products.

  1. 1
    Pizza Bot

    An inbox for AI agents that work in the background

    Pizza Bot is an inbox for long-running AI work. Start or schedule a task, walk away, and come back to finished work in Unread and decisions waiting in Action. Agents keep running when you disconnect, and the same app works on desktop, web a

    πŸ’¬ 0Yβ–² 61 on HNAI AgentsProductivityOpen Sourceby AI Launch Team

  2. 2
    Ordewell

    Turn one goal into an ordered plan of coding-agent tasks

    Ordewell turns one goal into an editable plan of coding-agent tasks. A read-only planner researches your repository, asks about anything unclear, and returns a dependency graph where each task names its agent, model and thinking effort. Ind

    πŸ’¬ 0Yβ–² 56 on HNCoding & Dev ToolsAI AgentsOpen Sourceby AI Launch Team

  3. 3
    Geiger

    See every AI agent on your machine and what it can touch

    Geiger is a read-only command that inventories every AI agent, harness, MCP server, plugin and AI extension on a machine, and explains in plain language what each one can touch. Run npx geiger-scan with no install, account or telemetry. Fi

    πŸ’¬ 0Yβ–² 49 on HNAI AgentsCoding & Dev ToolsOpen Sourceby AI Launch Team

  4. 4
    jevals

    Replacing LLM judges with typed Jev decisions

    jevals runs evals and guardrails for AI agents using Jev-style decision models instead of an LLM judge. All the checks for a trace, such as tool choice, groundedness, answer relevancy, prompt injection and PHI, go out as one request that co

    πŸ’¬ 0Yβ–² 47 on HNLLMs & InfrastructureAI AgentsOpen Sourceby AI Launch Team

  5. 5
    Foremerge

    Catch intent conflicts between parallel coding agents

    Foremerge is an open-source coordination protocol for coding agents, built on top of Git. Agents keep isolated worktrees but share intent, semantic claims, dependencies and provisional changes, so each one sees what the others are about to

    πŸ’¬ 0Yβ–² 45 on HNCoding & Dev ToolsAI AgentsOpen Sourceby AI Launch Team

  6. 6
    Moadim

    A scheduler for agents

    Moadim is an open-source loop engine that runs AI agents on a schedule. Define a loop with a prompt, a schedule and an agent, and it runs Claude, Codex, Hermes or Pi against your repo on every tick, each run in an isolated workbench with a

    πŸ’¬ 0Yβ–² 37 on HNAI AgentsCoding & Dev ToolsOpen Sourceby AI Launch Team

  7. 7
    aclif

    Agent CLI framework – one grammar – canonical names across SaaS

    aclif is a framework for building command-line tools that AI agents use to reach SaaS platforms. An agent gets one tool with one grammar and canonical names that reach the same record the same way on any platform, plus self-describing comma

    πŸ’¬ 0Yβ–² 35 on HNAI AgentsCoding & Dev ToolsOpen Sourceby AI Launch Team

  8. 8
    AURA

    A Rust agent that investigates and fixes production incidents

    AURA is a production-tested SRE agent platform from Mezmo that investigates and helps fix production incidents. Specialist agents correlate traces, logs, metrics and deployment history to find root causes and recommend fixes, using the mode

    πŸ’¬ 0Yβ–² 28 on HNAI AgentsLLMs & InfrastructureOpen Sourceby AI Launch Team

  9. 9
    OpenAPPA

    Open-source deterministic guardrails that don't break agents

    OpenAPPA is an information-flow policy engine that acts as a deterministic guardrail for LLM agents. It tracks how data flows instead of matching patterns, which the project says makes it fully resistant to data exfiltration from prompt inj

    πŸ’¬ 0Yβ–² 23 on HNAI AgentsLLMs & InfrastructureOpen Sourceby AI Launch Team

  10. 10
    49 Agents

    2D Canvas for Agents

    49 Agents is an open-source 2D agentic IDE: one zoomable canvas for all your agents, terminals, projects and machines. It shows Claude status on every pane, and adds a Monaco editor, git graph, issue tables, permission notifications and mar

    πŸ’¬ 0Yβ–² 18 on HNCoding & Dev ToolsAI AgentsOpen Sourceby AI Launch Team

  11. 11
    Egma

    Open-source simulation testing and monitoring for voice agents

    Egma is an open-source platform for testing voice agents and monitoring them in production. Build regression suites with simulated voice and text conversations and mocked tool responses, review real conversations with graders, and bring you

    πŸ’¬ 0Yβ–² 16 on HNAudio & VoiceAI AgentsOpen Sourceby AI Launch Team

  12. 12
    ENZO

    Self-hosted AI workspace with 300+ models, agents and skills on your own keys

    ENZO is an open-source, self-hosted AI workspace. Chat with over 300 models across 9 providers, build agents that draft their own operating manuals, and use 74 bundled skills, all on your own API keys. There's no ENZO account, usage meter o

    πŸ’¬ 0Yβ–² 16 on HNChatbots & AssistantsAI AgentsOpen Sourceby AI Launch Team

Related

Building one of these?

Launch it free