InnerVault

Library

85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.

Results

Looks like a goal we have a starting path for: I want to build an AI agent

  1. 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 yesterday

    git clone https://github.com/IvoryHeart/herdr-world.git
  2. pisper

    Agents & frameworks

    Multi-agent app for parallel sessions, tools, memory, workflows, desktop, terminal, and mobile.

    Stale GitHub, ling-kong-ran 313 ★MITUpdated 6 days ago

    git clone https://github.com/ling-kong-ran/pisper.git
  3. nimbalyst

    Agents & frameworks

    Nimbalyst - The open-source visual workspace for Claude Code, Codex, and OpenCode. Run multiple coding agents in parallel, edit their work visually in markdown, mockups, and diagrams, and track tasks. Free, MIT-licensed desktop app for macOS, Windows, Linux, with mobile companion for iOS and Android.

    Stale GitHub, nimbalyst 2,051 ★MITUpdated 6 days ago

    git clone https://github.com/nimbalyst/nimbalyst.git
  4. legend-talk

    Agents & frameworks

    Multi-round AI roundtable with 161 great thinkers. They debate each other, not just answer you | 与历史上最伟大的思想家进行圆桌会议

    Stale GitHub, rockbenben 57 ★MITUpdated 25 days ago

    git clone https://github.com/rockbenben/legend-talk.git
  5. friday

    Agents & frameworks

    A local-first desktop alternative to Grok Bot, OpenBot, T3 Code, Herdr and Orca. Run Claude Code, Codex, Cursor and 13 more coding agents as one team on your own computer: a shared board, agents that check each other’s work, and no account. Free. macOS, Windows, Linux.

    Indexed GitHub, splashxmoon 67 ★MITUpdated yesterday

    git clone https://github.com/splashxmoon/friday.git
  6. life-distributable

    Agents & frameworks

    A personal agent that works on your life around the clock, on a Mac you own. One sentence to Claude Code installs it.

    Indexed GitHub, mattabate 411 ★MITUpdated yesterday

    git clone https://github.com/mattabate/life-distributable.git
  7. ScienceClaw

    Agents & frameworks

    ScienceClaw is a personal research assistant built with LangChain DeepAgents and AIO Sandbox infrastructure, adopting a completely new architecture beyond OpenClaw. It offers stronger security, better transparency, and a more user-friendly experience.

    Stale GitHub, AgentTeam-TaichuAI 670 ★Updated 6 months ago

    git clone https://github.com/AgentTeam-TaichuAI/ScienceClaw.git
  8. Universal SKILL.md catalog for research workflows: literature review, research design, project memory, manuscript writing, and cross-agent delegation for Claude Code, Codex, Gemini, Cursor, OpenClaw, and generic AI clients.

    Indexed GitHub, WenyuChiou 667 ★MITUpdated today

    git clone https://github.com/WenyuChiou/ai-research-skills.git
  9. agent-fleet-o

    MCP servers

    Open-source AI agent orchestration platform — self-hosted mission control for autonomous multi-agent systems. Visual DAG workflows, 670+ MCP tools, human-in-the-loop approvals. Works with Claude, GPT-4o, Gemini, Ollama, Codex.

    Stale GitHub, escapeboy 81 ★AGPL-3.0Updated 4 days ago

    git clone https://github.com/escapeboy/agent-fleet-o.git
  10. myPKA

    Agents & frameworks

    AI-powered Personal Knowledge Assistance in a folder. Built on the ICOR methodology. Plain markdown. Any LLM. Yours forever.

    Stale GitHub, myICOR 319 ★MITUpdated 14 days ago

    git clone https://github.com/myICOR/myPKA.git
  11. ai-platform-engineering

    AI repositories

    CAIPE is an open-source AI platform for building, governing, and operating AI agents and agentic workflows for platform engineering and beyond.

    Indexed GitHub, caipe-io 445 ★Apache-2.0Updated today

    git clone https://github.com/caipe-io/ai-platform-engineering.git
  12. cleancode

    Agents & frameworks

    Canvas for orchestrating Claude Code, Codex, and CLI agents in parallel. Delegate tasks and build reusable AI workflows.

    Indexed GitHub, chen-985211 114 ★MITUpdated today

    git clone https://github.com/chen-985211/cleancode.git
  13. awesome-hermes-agent-zh

    Agents & frameworks

    Hermes Agent中文站- 中文实战入口:上手路径、国内落地、OpenClaw 共存迁移、排障参考与可下载方案包。

    Stale GitHub, zcweah1981 56 ★Updated 7 days ago

    git clone https://github.com/zcweah1981/awesome-hermes-agent-zh.git
  14. lavern

    MCP servers

    An agentic law firm. Yours. 67 specialist AI agents that review documents through evidence-backed debate, with mandatory human gates and a 10-pass verification loop. Apache 2.0.

    Stale GitHub, AnttiHero 311 ★Apache-2.0Updated 2 months ago

    git clone https://github.com/AnttiHero/lavern.git
  15. hive-mcp

    MCP servers

    MCP server for hive-framework development. A memory and agentic coordination solution.

    Stale GitHub, hive-agi 29 ★Custom licence (see repository)Updated 8 days ago

    git clone https://github.com/hive-agi/hive-mcp.git
  16. 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 yesterday

    git clone https://github.com/majiayu000/harness.git
  17. LLM-PySC2

    Agents & frameworks

    LLM-PySC2 is NKAI Decision Team and NUDT Decision Team's Python component of the StarCraft II LLM Decision Environment. It exposes Deepmind's PySC2 Learning Environment API as a Python LLM Environment.

    Stale GitHub, NKAI-Decision-Team 162 ★Apache-2.0Updated 19 months ago

    git clone https://github.com/NKAI-Decision-Team/LLM-PySC2.git
  18. agentic-ai

    AI repositories

    Agentic AI research papers, benchmarks, frameworks, and tools curated across 24 domains.

    Indexed GitHub, mahmoudrabie 193 ★MITUpdated 2 days ago

    git clone https://github.com/mahmoudrabie/agentic-ai.git
  19. learn-claude-code-rs

    Docs & tutorials

    Build an AI agent harness in Rust, from a minimal loop to tools, subagents, memory, teams, worktrees, MCP, and typed tool routing.

    Stale GitHub, wulawulu 146 ★MITUpdated 28 days ago

    git clone https://github.com/wulawulu/learn-claude-code-rs.git
  20. bothouse

    Agents & frameworks

    把 Claude Code、Codex、Gemini 拉进一个群,组长 AI 分活,大家共用一份记忆。| Put Claude Code, Codex and Gemini CLI in one Discord group: a team-lead AI splits the work, and they share one memory.

    Indexed GitHub, zuiho-kai 231 ★Apache-2.0Updated today

    git clone https://github.com/zuiho-kai/bothouse.git
  21. The centralized Headquarters for the Cognitive Lead AI multi-agent system. Features hallucination-resistant system prompts, MCP servers, and strict Agent Skills.

    Stale GitHub, mokhtarabadi 8 ★MITUpdated 19 days ago

    git clone https://github.com/mokhtarabadi/cognitive-lead-hq.git
  22. agentdb

    Agents & frameworks

    Vector memory that gets smarter every time your agent uses it.

    Stale GitHub, ruvnet 97 ★MITUpdated 5 days ago

    git clone https://github.com/ruvnet/agentdb.git
  23. opus-manager

    Agents & frameworks

    Make Claude the manager, not the coder: one skill that hands work to cheaper AI CLIs, verifies the results, and gets a second vendor to review.

    Indexed GitHub, yanauto 63 ★MITUpdated yesterday

    git clone https://github.com/yanauto/opus-manager.git
  24. wenflow

    Agents & frameworks

    先说清你想解决的事,再开始学习。问流 WenFlow:从真实问题出发的开源 AI 学习路径原型——对话澄清目标、生成可执行路径、回合式教学、遗忘曲线复习、学习负荷追踪(LSS/KTL/LF/LSB);自带 18 页管理后台与虚拟学习者仿真。Vue3 + Node.js + SQLite,MIT,可自托管。早期实验原型。

    Stale GitHub, wenflow-org 68 ★MITUpdated 4 days ago

    git clone https://github.com/wenflow-org/wenflow.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.