InnerVault

Library

85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. resp-warden-desk

    Agents & frameworks

    An eight-agent rule engine for on-chain risk analysis. Seven rules propose, one vetoes. Read-only, no keys, no execution.

    Indexed GitHub, ElysiumduskImmortal63439 50 ★Updated 3 days ago

    git clone https://github.com/ElysiumduskImmortal63439/resp-warden-desk.git
  2. harness

    Agents & frameworks

    Run fleets of parallel coding agents with governance — Rust control plane for Claude Code & Codex: orchestration, policy, cross-agent review, observability.

    Indexed GitHub, majiayu000 92 ★MITUpdated 2 days ago

    git clone https://github.com/majiayu000/harness.git
  3. synkora-ai

    Agents & frameworks

    Open-source AI agent platform for building, deploying, and managing AI teammates. Role-based agents (PM, Engineer, Support, Marketing) with custom tools, knowledge bases, and 50+ integrations. Self-hosted, multi-provider LLM support, no vendor lock-in.

    Indexed GitHub, getsynkora 57 ★MITUpdated 4 days ago

    git clone https://github.com/getsynkora/synkora-ai.git
  4. Bittune

    Agents & frameworks

    Local-first engineering agent that deploys, benchmarks and tunes vLLM/SGLang inference services on your own GPUs, with auditable run evidence.

    Indexed GitHub, bitcloud-ai 304 ★MITUpdated 4 days ago

    git clone https://github.com/bitcloud-ai/Bittune.git
  5. herdr-world

    Agents & frameworks

    Herdr World — visualize agent work in Office, Tree, Graph, and Spaces; control Herdr agents across local and SSH hosts.

    Indexed GitHub, IvoryHeart 52 ★MITUpdated 2 days ago

    git clone https://github.com/IvoryHeart/herdr-world.git
  6. Xenon

    Agents & frameworks

    Verifiable AI coding agent harness / 可验证的 AI 编码代理:evidence hash-chain · hollow-answer gate · manual verification checklist · 6 engines + MCP · multi-model · Windows/CJK · listed in awesome-opensource-ai & Collabnix awesome-mcp-lists

    Indexed GitHub, xianyu-sheng 56 ★MITUpdated yesterday

    git clone https://github.com/xianyu-sheng/Xenon.git
  7. SuperNovaAgent

    Agents & frameworks

    SuperNova is a Windows-first desktop AI Workbench that turns chat into traceable tasks. It combines a Tauri + React Workbench, Rust Product Runtime, typed protocol, and Process Kernel so actions can produce visible artifacts, runtime receipts, replayable evidence, and controlled workspace execution.

    Stale GitHub, Ray-Code-Svg 187 ★Apache-2.0Updated 4 months ago

    git clone https://github.com/Ray-Code-Svg/SuperNovaAgent.git
  8. pragma

    Agents & frameworks

    Build portable agent teams across models and harnesses, with shared memory, skills, tools, and workflows — then bring them into Codex, Claude Code, or any AI system you build. 构建跨 harness 和模型的可移植 Agent Team,共享记忆、技能、工具和工作流,一次构建,接入 Codex、Claude Code 或任何 AI 系统。

    Stale GitHub, pqpo 233 ★AGPL-3.0Updated 8 days ago

    git clone https://github.com/pqpo/pragma.git
  9. DataParasite

    Agents & frameworks

    A simple yet versatile context engineered for scalable online data collection

    Stale GitHub, mengysun 102 ★BSD-3-ClauseUpdated 25 days ago

    git clone https://github.com/mengysun/DataParasite.git
  10. adhdev

    Agents & frameworks

    🦦 ADHDev — Agent Dashboard Hub. Monitor & control AI coding agents from a single dashboard. Self-hosted, open-source.

    Stale GitHub, vilmire 118 ★AGPL-3.0Updated 7 days ago

    git clone https://github.com/vilmire/adhdev.git
  11. maestro-flow

    Agents & frameworks

    Intent-driven workflow orchestration for multi-agent AI development — adaptive lifecycle engine, self-reinforcing knowledge graph, and visual dashboard for Claude Code, Gemini, Codex & more

    Stale GitHub, catlog22 568 ★Updated 22 days ago

    git clone https://github.com/catlog22/maestro-flow.git
  12. pentest-ai-agents

    Agents & frameworks

    Turn Claude Code into your offensive security research assistant. Specialized AI subagents for authorized penetration testing plan engagements, analyze recon, research exploits, build detections, audit STIGs, and write reports.

    Stale GitHub, 0xSteph 2,330 ★MITUpdated 42 days ago

    git clone https://github.com/0xSteph/pentest-ai-agents.git
  13. SoduWork

    Agents & frameworks

    The AI-native engine for teams and their agents. Multi-harness, multi-agent, self-hosted.

    Indexed GitHub, mdiri-ai 998 ★MITUpdated yesterday

    git clone https://github.com/mdiri-ai/SoduWork.git
  14. interlock

    Agents & frameworks

    Spec-driven development for Claude Code, layered on OpenSpec. You read one spec; parallel agents ship it to a tested commit.

    Stale GitHub, renzrollon 62 ★MITUpdated 6 days ago

    git clone https://github.com/renzrollon/interlock.git
  15. dsh-auto-memory

    Agents & frameworks

    Trustworthy memory for DeepSeek Harness — 4-state trust machine, evidence chains, audited injections. Zero servers, just Markdown.

    Indexed GitHub, AskTheWay 132 ★MITUpdated 3 days ago

    git clone https://github.com/AskTheWay/dsh-auto-memory.git
  16. open-mercato

    Agents & frameworks

    The AI-Engineering Foundation Framework for business apps: open-source TypeScript, with multi-tenancy, RBAC, events and domain modules already decided as conventions and specs, so Cursor, Claude Code and Codex build features instead of re-deciding architecture. Start with 80% done.

    Indexed GitHub, open-mercato 1,936 ★MITUpdated yesterday

    git clone https://github.com/open-mercato/open-mercato.git
  17. neoism

    Agents & frameworks

    A GPU-rendered, terminal-first workspace: Agent framework, real shells, IDE, Markdown, and multiplayer — one Rust engine.

    Stale GitHub, parkers0405 128 ★Custom licence (see repository)Updated 9 days ago

    git clone https://github.com/parkers0405/neoism.git
  18. Network-AI

    Agents & frameworks

    Traffic light for AI Agents and TypeScript/Node multi-agent orchestrator with shared state, guardrails, and adapters for 32 AI frameworks

    Stale GitHub, Jovancoding 89 ★MITUpdated 8 days ago

    git clone https://github.com/Jovancoding/Network-AI.git
  19. cubeloop

    Agents & frameworks

    CubeLoop — a Pythonic, async-native agent harness core designed for high performance, readability, and production-grade persistence.

    Stale GitHub, cubeplexai 89 ★MITUpdated 11 days ago

    git clone https://github.com/cubeplexai/cubeloop.git
  20. Lumi_Nox

    Agents & frameworks

    Two AI VTubers co-hosting one live show — the realtime engine & orchestration. Open-core, battle-tested by a daily stream.

    Indexed GitHub, MIO-456 246 ★MITUpdated 3 days ago

    git clone https://github.com/MIO-456/Lumi_Nox.git
  21. orloj

    Agents & frameworks

    An orchestration runtime for multi-agent AI systems. Declare agents, tools, and policies as YAML; Orloj schedules, executes, routes, and governs them for production-grade operation.

    Indexed GitHub, OrlojHQ 126 ★Apache-2.0Updated 7 days ago

    git clone https://github.com/OrlojHQ/orloj.git
  22. anything2explainer

    Agents & frameworks

    Topic in, narrated explainer video out. A Claude Code / Codex skill that turns any topic into a black-canvas motion-graphics explainer video with TTS voiceover, subtitles and a chapter progress bar. Chinese or English; every frame drawn in code with Remotion.

    Indexed GitHub, Vincentwei1021 3,343 ★Custom licence (see repository)Updated 2 days ago

    git clone https://github.com/Vincentwei1021/anything2explainer.git
  23. open-code-review

    Agents & frameworks

    AI-powered multi-agent code review. Simulates a customizable team of Engineers performing code review with built-in discourse.

    Stale GitHub, spencermarx 384 ★Apache-2.0Updated 6 days ago

    git clone https://github.com/spencermarx/open-code-review.git
  24. WorldSeed

    Agents & frameworks

    More is Different. A multi-agent world engine where AI agents live, talk, compete, ally.

    Stale GitHub, AIScientists-Dev 821 ★MITUpdated 6 months ago

    git clone https://github.com/AIScientists-Dev/WorldSeed.git

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.