InnerVault

Library

86,219 resources from 11 public sources. 46 checked by hand; the rest are unreviewed.

Results

1,410 results Clear search and filters
  1. EDAgent

    Agents & frameworks

    Multi-agent exploratory data analysis system with autonomous insights, visualization, preprocessing, and reporting workflows.

    Stale GitHub, Varn1t 50 ★Updated 16 days ago

    git clone https://github.com/Varn1t/EDAgent.git
  2. StrataGate-AgentMemory

    Agents & frameworks

    Recent memories stay detailed. Older ones grow concise. Important ones live on.近期记忆保持详细,旧记忆逐渐精简,重要记忆长期存在。

    Indexed GitHub, diqierjia 119 ★MITUpdated today

    git clone https://github.com/diqierjia/StrataGate-AgentMemory.git
  3. claude-code-source-analysis

    Agents & frameworks

    Claude Code 源码深度研究,包括 Foundations/Execution/Infrastructure 三大章节和 23 个子系统的架构分析拆解。

    Stale GitHub, xiaonancs 91 ★Custom licence (see repository)Updated 5 months ago

    git clone https://github.com/xiaonancs/claude-code-source-analysis.git
  4. soul

    Agents & frameworks

    Soul: The Persistent Memory Layer for Multi-Agent Systems. High-performance session orchestration with SQLite-based KV-Cache for MCP. Give your AI agents a soul that never forgets.

    Stale GitHub, choihyunsus 68 ★Custom licence (see repository)Updated 9 days ago

    git clone https://github.com/choihyunsus/soul.git
  5. joyczl-agent

    Agents & frameworks

    Joy — a local-first personal assistant. Rust core (loop / memory / tools / graph / evals), TypeScript gateways + dashboard, Python thin SDK.

    Indexed GitHub, ChrisVip001 112 ★MITUpdated yesterday

    git clone https://github.com/ChrisVip001/joyczl-agent.git
  6. openhermit

    Agents & frameworks

    OpenHermit is the open-source platform for deploying fleets of AI agents as production services — durable state, sandboxed execution, managed at scale, and the channels you already use.

    Indexed GitHub, HCF-STUDIOS 90 ★MITUpdated 5 days ago

    git clone https://github.com/HCF-STUDIOS/openhermit.git
  7. job-hunter-team

    Agents & frameworks

    A team of AI agents that runs your job search — self-hosted, on your own LLM subscription. MIT.

    Stale GitHub, leopu00 53 ★MITUpdated 13 days ago

    git clone https://github.com/leopu00/job-hunter-team.git
  8. open-dynamic-workflows

    Agents & frameworks

    Open Dynamic Workflows: TypeScript CLI runtime for Claude Code-style dynamic workflows across Codex, Claude Code, Gemini, Qwen, Kimi, and custom coding-agent CLIs.

    Stale GitHub, xz1220 111 ★MITUpdated 29 days ago

    git clone https://github.com/xz1220/open-dynamic-workflows.git
  9. stim

    Agents & frameworks

    Fast, isolated, local React Native and Expo environments for coding agents. Shared build caches, parallel worktrees, owned devices, and safe cleanup.

    Indexed GitHub, appandflow 103 ★MITUpdated today

    git clone https://github.com/appandflow/stim.git
  10. DuDuClaw

    Agents & frameworks

    Turn AI coding CLIs (Claude Code, Codex, Antigravity) into AI employees on LINE, Telegram, Discord, Slack and 7 more chat apps. A judge reviews each result, every cost is logged, memory stays on your machine. Also runs as a standalone MCP memory server. Self-hosted, Apache 2.0.

    Indexed GitHub, zhixuli0406 51 ★Apache-2.0Updated today

    git clone https://github.com/zhixuli0406/DuDuClaw.git
  11. agent-message-queue

    Agents & frameworks

    File-based message queue for local agent-to-agent communication (Maildir-style)

    Indexed GitHub, avivsinai 94 ★MITUpdated today

    git clone https://github.com/avivsinai/agent-message-queue.git
  12. 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 2 days ago

    git clone https://github.com/yanauto/opus-manager.git
  13. OmicsClaw

    Agents & frameworks

    Conversational & memory-enabled AI research partner for multi-omics analysis. CLI + Desktop App (installers in Releases). From biological idea to full research paper.

    Stale GitHub, TianGzlab 161 ★Apache-2.0Updated 41 days ago

    git clone https://github.com/TianGzlab/OmicsClaw.git
  14. prodagent

    Agents & frameworks

    A minimal, readable agent-framework kernel — understand how LangGraph/ADK work under the hood. 1800行代码的 agent 框架内核,理解 LangGraph/ADK 底层的工作原理

    Stale GitHub, limenagent 122 ★MITUpdated 27 days ago

    git clone https://github.com/limenagent/prodagent.git
  15. imp

    Agents & frameworks

    Run large AI chat models privately on your own NVIDIA RTX 50 or RTX PRO graphics card. On one RTX 5090, Qwen3.8-27B writes about 70 words per second, 1.4x faster than vLLM. Even a model almost four times larger than the card's memory runs. Works with apps made for ChatGPT or Claude. Starts with one docker command.

    Stale GitHub, kekzl 124 ★MITUpdated 13 days ago

    git clone https://github.com/kekzl/imp.git
  16. swarm-orchestrator

    Agents & frameworks

    A local coding agent: give it a task, it makes the change, checks each requirement with swarm-verify, and returns the patch with signed evidence of what is done.

    Stale GitHub, moonrunnerkc 113 ★ISCUpdated 13 days ago

    git clone https://github.com/moonrunnerkc/swarm-orchestrator.git
  17. reins

    Agents & frameworks

    A lightweight agent harness you bolt onto your app so an LLM can operate it — safely, and cheaply.

    Stale GitHub, shamspias 92 ★MITUpdated 4 months ago

    git clone https://github.com/shamspias/reins.git
  18. EdgeBox

    Agents & frameworks

    A fully-featured, GUI-powered local LLM Agent sandbox with complete MCP protocol support. Features both CLI and full desktop environment, enabling AI agents to operate browsers, terminal, and other desktop applications just like humans. Based on E2B oss code.

    Stale GitHub, BIGPPWONG 212 ★GPL-3.0Updated 6 months ago

    git clone https://github.com/BIGPPWONG/EdgeBox.git
  19. 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 · single-loop kernel + bidirectional MCP · multi-model · Windows/CJK · listed in awesome-opensource-ai & Collabnix awesome-mcp-lists

    Indexed GitHub, xianyu-sheng 56 ★MITUpdated today

    git clone https://github.com/xianyu-sheng/Xenon.git
  20. Jixu

    Agents & frameworks

    Durable single-Agent Harness for TypeScript: recoverable Threads, context continuity, explicit side effects, and a native TUI.

    Stale GitHub, joe960913 93 ★MITUpdated 48 days ago

    git clone https://github.com/joe960913/Jixu.git
  21. joxo

    Agents & frameworks

    Team workspace for AI coding agents: your Claude Code, Codex, Cursor, Gemini CLI and OpenCode agents share one project, task board and handoffs. Desktop, iPhone and MCP server.

    Stale GitHub, JoxoAI 57 ★Custom licence (see repository)Updated 9 days ago

    git clone https://github.com/JoxoAI/joxo.git
  22. alans-way

    Agents & frameworks

    Alan's Way: a Mac app where your Hermes bots drive their own browser tabs on your Mac and a cloud VPS, with Telegram alongside and handoff between the two.

    Stale GitHub, capthvnsen 105 ★MITUpdated 9 days ago

    git clone https://github.com/capthvnsen/alans-way.git
  23. novel-engine

    Agents & frameworks

    Novel Engine is a desktop app that lets you construct novels. Seven AI agents handle the editorial pipeline — from pitch to published manuscript — while you focus on the story. Powered by Claude, Codex, and Ollama. Open source. Free. No gatekeeping.

    Stale GitHub, john-paul-ruf 78 ★AGPL-3.0Updated 9 days ago

    git clone https://github.com/john-paul-ruf/novel-engine.git
  24. software-periodic-table

    Agents & frameworks

    A finite ontology of 115 recurring software elements and a composition framework for LLM-based coding agents

    Stale GitHub, NullLabTests 86 ★MITUpdated 9 days ago

    git clone https://github.com/NullLabTests/software-periodic-table.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.