long-running-agents repositories

Trending repositories tagged long-running-agents, ranked by trending score. Updated daily.

  1. 1
    orwa-mahmoud/nightshift

    Accountable long-running coding shifts for Cursor, Codex, and Claude Code. Safe autonomy, recovery, persistent state, and reviewable results: a clear view of what’s done, in progress, parked, or blocked—without scrolling a marathon chat.

    GitHub · Shell · 570 stars · 24 forks · +66 stars in 24 hours · Trending score 3.38

  2. 2
    OthmanAdi/planning-with-files

    Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, session recovery after /clear and compaction, per-turn re-injection against context rot, deterministic completion gate. Manus-style. Install from npm, the Claude Code plugin marketplace, or npx skills. Codex, Cursor, OpenCode, 60+ agents.

    GitHub · Shell · 28,166 stars · 2,322 forks · +33 stars in 24 hours · Trending score 3.00

  3. 3
    arcee-ai/nac

    Give AI agents ambitious work without losing the plot. nac is an open-source harness for long-running tasks, using a central orchestrator, threads, and structured episodes to stay aligned with your intent.

    GitHub · Rust · 317 stars · 36 forks · +1 stars in 24 hours · Trending score 1.23

  4. 4
    alexgreensh/outsourcerer

    Make your AI agents work as a team. You keep working in 1 session while it orchestrates models via your other subscriptions, local models and more. Run a Software Factory: long plans, proven steps, safe merges. Carries your setup, tracks every cost.

    GitHub · Shell · 199 stars · 18 forks · +1 stars in 24 hours · Trending score 1.00

  5. 5
    5dive-ai/5dive

    Run your own AI team from your phone. Claude Code, Codex and more on your own server: shared tasks, always-on agents, a small composable bash core. MIT. An open-source alternative to Grok Bot and OpenAI Dots.

    GitHub · Shell · 123 stars · 14 forks · 0 stars in 24 hours · Trending score 0.58

  6. 6
    Innocent-children/TaskBelay

    Task control for AI coding agents: explicit scope, bounded verification, durable state, safe recovery. Codex · Claude Code · DeepSeek · ZCode.

    GitHub · Go · 13 stars · 0 forks · 0 stars in 24 hours · Trending score 0.04

  7. 7
    mims-harvard/AutoScientists

    AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation

    GitHub · Python · 800 stars · 127 forks · 0 stars in 24 hours · Trending score 0.00

  8. 8
    didvc/ai-bwrap

    Better agentic security inside a sandbox; one wrapper, any agent.

    GitHub · Shell · 34 stars · 6 forks · 0 stars in 24 hours · Trending score 0.00

  9. 9
    cayu-dev/cayu

    Cayu is an open-source Python framework for building and running domain-specific long-horizon agents, with a durable runtime built in.

    GitHub · Python · 848 stars · 80 forks · 0 stars in 24 hours · Trending score 0.00

  10. 10
    i365dev/free4chat

    Temporary rooms for Humans and AI Agents — run, supervise and steer Agent Tasks without a permanent workspace.

    GitHub · TypeScript · 1,221 stars · 170 forks · 0 stars in 24 hours · Trending score 0.00

  11. 11
    demeyer1/Autobot

    Self-improving agent harness for ChatGPT and Codex on Mac. #1 on AssistantBench. On-disk memory, privacy zones, verified completion.

    GitHub · Shell · 24 stars · 1 forks · 0 stars in 24 hours · Trending score 0.00

  12. 12
    vkuprin/ralph-harness

    Runs Claude Code in a loop for days. Every iteration is a fresh claude -p, and a commit ships only if your own checks pass.

    GitHub · TypeScript · 5 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00

  13. 13
    1Lany2a/dsh-domain-role

    Domain-identity framework for long-running AI agents: one domain, one long-lived identity, one accountable owner, one audit trail. 域身份体系 —— 域桥插件 dsh-domain-bridge v0.6.4(npm 可装 / 11 个工具 / 282 用例契约测试)+ 协作框架文档 + 角色模板。

    GitHub · JavaScript · 11 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00