Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
LangGraph
Agents & frameworksA framework for building agents as graphs of steps, for long-running work that needs to pause, retry or resume.
pip install -U langgraph -
caura-long-run-fleet
Agents & frameworksLong-running fleet orchestration and memory infrastructure for AI agents. Enables persistent context, shared memory, task execution, and governed coordination across multi-agent systems.
git clone https://github.com/caura-ai/caura-long-run-fleet.git -
goskill
Tools & apps长任务执行 Skill:先定成功标准再逐轮验收,让 Claude Code/Codex 跑完长任务不半途而废|Goal-driven long-running agent tasks
git clone https://github.com/AIPMAndy/goskill.git -
planning-with-files
SkillsPersistent 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.
git clone https://github.com/OthmanAdi/planning-with-files.git -
agentscope-java
Agents & frameworksBuild distributed, production-grade, long-running agents.
git clone https://github.com/agentscope-ai/agentscope-java.git -
nac
MCP serversGive 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.
git clone https://github.com/arcee-ai/nac.git -
long-run-hybrid-coach
SkillsAdaptive running and strength coaching for the long run — a hosted MCP server and Agent Skill that keeps one current 28-day plan in step with your Intervals.icu evidence. Independent project, not affiliated with Garmin or Intervals.icu.
git clone https://github.com/atomchung/long-run-hybrid-coach.git -
nightshift
Agents & frameworksAccountable 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.
git clone https://github.com/orwa-mahmoud/nightshift.git -
free4chat
Agents & frameworksTemporary rooms for Humans and AI Agents — run, supervise and steer Agent Tasks without a permanent workspace.
git clone https://github.com/i365dev/free4chat.git -
CodeMachine-CLI
AI repositoriesCodeMachine is an open-source tool that orchestrates AI coding agents into repeatable, long-running workflows. ⚡️
git clone https://github.com/moazbuilds/CodeMachine-CLI.git -
cadence
Tools & appsCadence is a distributed, scalable, durable, and highly available orchestration engine to execute asynchronous long-running business logic in a scalable and resilient way.
git clone https://github.com/cadence-workflow/cadence.git -
agentscope-java
Agents & frameworksBuild distributed, production-grade, long-running agents.
git clone https://github.com/agentscope-ai-java/agentscope-java.git -
kheish
AI repositoriesOrchestration engine for long-running, tool-using AI agents
git clone https://github.com/graniet/kheish.git -
crabtalk-20261010
Agents & frameworksThe long-running embedded agent
git clone https://github.com/crabtalk/crabtalk-20261010.git -
cc-sdd
SkillsTurn approved specs into long-running autonomous implementation. A minimal, adaptable SDD harness with Agent Skills for Claude Code, Codex, Cursor, Copilot, Windsurf, OpenCode, Gemini CLI, and Antigravity.
git clone https://github.com/gotalab/cc-sdd.git -
aigent-os
SkillsClaude Code harness and alternative to context compaction: at 80% context it writes a verified capsule, runs /clear and resumes with persistent memory in git. Long-running and multi-agent Claude Code sessions, auto clear instead of auto-compact. MIT, local, Node 18+. Codex adapter.
git clone https://github.com/wrg32786/aigent-os.git -
codex-long-jobs
SkillsBackground jobs for OpenAI Codex CLI and VS Code: run long tasks without model polling and wake the original session on completion.
git clone https://github.com/zycdev/codex-long-jobs.git -
OpenHarness
Agents & frameworksReliability harness for long-running OpenClaw agents: persistent state, strict task contracts, scheduled execution, and external validation.
git clone https://github.com/thu-nmrc/OpenHarness.git -
MPM-Coding
MCP serversLocal MCP server for reliable long-running AI coding workflows.
https://github.com/halflifezyf2680/MPM-Coding/releases/download/v1.15.1/mpm-vibe-coding-v1.15.1.mcpb@1.15.1 -
Codex Control Plane MCP
MCP serversDurable MCP control plane for long-running Codex Desktop tasks.
codex-control-plane-mcp@0.2.1 -
UNITARES
MCP serversAccountability infrastructure for long-running AI agents. Shared memory is a provenance graph.
-
golutra
Agents & frameworksMulti-agent AI orchestration platform for automation, workflows, and developer tools. Golutra transforms Codex, Claude Code, and OpenClaw into a unified agent system with parallel execution, task orchestration, long-running workflows, and AI productivity workspace.
git clone https://github.com/golutra/golutra.git -
zenith
MCP serversZenith: a continuous-improvement harness for long-running agent tasks. Turns Claude Code, Codex, or Hermes into a multi-agent mission orchestrator via MCP/ACP.
git clone https://github.com/Intelligent-Internet/zenith.git -
chief-of-staff
SkillsPursue a long-running goal in a single session by co-ordinating subagents.
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.