Library
85,340 resources from 11 public sources. 54 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
-
rhizome
SkillsRhizome lets Claude Code, Codex, and OpenCode sessions discover each other, follow selected work, and exchange messages through MCP. Use it to coordinate parallel tasks on your laptop or connect your agents with a colleague's agents over a LAN or Tailscale network.
git clone https://github.com/aliengiraffe/rhizome.git -
Aura
MCP serversSelf-hosted AI agent in Go with temporal graph memory, scheduled jobs, MCP tools and Telegram/WhatsApp channels. Docker Compose appliance, MIT.
git clone https://github.com/chetto1983/Aura.git -
trace-to-practice
SkillsEvidence-backed retrospectives for AI coding-agent histories. Offline indexing, scoped workflow improvements, and bilingual documentation.
git clone https://github.com/wssfk12138/trace-to-practice.git -
Yosuri
Tools & appsYosuri — LESS CHAT, MORE AUTOMATIC. A 24H self-evolving AI agent that aggregates free models into one OpenAI & Anthropic-compatible API, picks its own tasks, writes real code, and verifies results. Local-first, free forever. AGPL-3.0.
git clone https://github.com/Rescenix/Yosuri.git -
dotbrain
SkillsKeeps your project's context private and your code repo clean
git clone https://github.com/arminzou/dotbrain.git -
Noosphere
SkillsThe live network for high-quality Agent Skills — discover the latest verified versions, publish your own, and communicate agent-to-agent via MCP.
git clone https://github.com/JinNing6/Noosphere.git -
hippo-memory
MCP serversStop re-teaching your agent. Make your agent's memory work like a brain. Hippo is long-term memory for coding agents. It's a critical layer for your AI harness that connects across your different tools (Cursor, Claude Code, Codex). Local-first. Measured: about half the repeat mistakes of built-in memory alone, at the same cost.
git clone https://github.com/kitfunso/hippo-memory.git -
cortadel
SkillsSelf-hosted long-term temporal graph memory for AI agents — MCP, REST and a dashboard in one container, with FalkorDB or Memgraph.
git clone https://github.com/cortadel/cortadel.git -
mind-mem
MCP serversPersistent AI memory for Claude Code, OpenClaw, and any MCP-compatible agent. BM25F + vector hybrid, governance-aware, local-first, zero-infrastructure.
git clone https://github.com/star-ga/mind-mem.git -
jarvis-os
SkillsA memory hub and curated skill set for Claude Code — persistent memory that loads from any directory, plus a guided local setup.
git clone https://github.com/ManceRayder42/jarvis-os.git -
dkg
Agents & frameworksOriginTrail Decentralized Knowledge Graph (DKG) — Shared memory for AI agents. Give Hermes, OpenClaw, Claude Code, Codex, and Cursor a local knowledge-graph memory that several agents can share, with provenance, and verify on-chain when it matters. Open source, Apache-2.0.
git clone https://github.com/OriginTrail/dkg.git -
brigade
SkillsBrigade Stack: run coding agents anywhere and keep one record of the work. Shared tasks, claims, verification receipts, handoffs, and MCP and skills sync for Claude Code, Codex, Cursor, OpenCode, and T3 Code.
git clone https://github.com/escoffier-labs/brigade.git -
enquire-mcp
MCP serversThe #1 Obsidian MCP for AI memory — freshness-aware, cited, local-first and read-only by default. Dataview, Bases, PDFs, every agent.
git clone https://github.com/oomkapwn/enquire-mcp.git -
claude-bible
SkillsMake Claude Code behave consistently across repos, sessions and humans: rules-as-files governance with precedence, declined-decisions journal, objection sparring. Sanitized from a live production system. Free, MIT.
git clone https://github.com/tonydzi/claude-bible.git -
kana
SkillsLightweight, untracked, and self-evolving terminal AI companion. Zero telemetry, durable memory, bidirectional synergy, and native TUI.
git clone https://github.com/longyijdos/kana.git -
memtrust
MCP serversIndependent, reproducible benchmark harness for agent-memory backends.
memtrust-cli@0.3.6 -
memex
MCP serversZettelkasten-based agent memory system with bidirectional links
@touchskyer/memex@0.1.8 -
EGC
MCP serversEGC gives every AI coding agent the same brain. Shared memory, skills, and live context across Cursor, Claude Code, Copilot, Aider, and 29 AI coding tools with zero configuration. Every tab, terminal, and AI stays automatically synchronized. One brain. Everywhere.
git clone https://github.com/Fmarzochi/EGC.git -
ai-security-research-radar
SkillsAI Security Research Radar — AI for security and security for AI
git clone https://github.com/Neetx/ai-security-research-radar.git -
Agent Recall Trail
MCP serversPrivate Agent memory and governed shared knowledge.
https://github.com/fantasyce/agent-recall-trail/releases/download/v0.3.7/agent-recall-trail_0.3.7.mcpb@0.3.7 -
skein-js
SkillsOpen-source alternative to LangGraph Platform for TypeScript — self-host your LangGraph.js agents behind the standard Agent Protocol API. Your infra, your Postgres, no vendor lock-in. Drop-in for the LangGraph CLI.
git clone https://github.com/skein-js/skein-js.git -
llmslim
MCP serversLong-term memory for AI agents with no LLM call: an MCP server and Claude Code plugin, plus local-first context compression for LLM apps.
git clone https://github.com/Thanatos9404/llmslim.git -
claude-mem-lite
MCP serversPersistent long-term memory for Claude Code via MCP — captures coding decisions, bugfixes, and context across sessions. Hybrid FTS5 + TF-IDF search with episode batching. Single SQLite DB, no external services. Alternative to claude-mem with 600x lower cost.
git clone https://github.com/sdsrss/claude-mem-lite.git -
aios
Agents & frameworksThe local-first control plane for long-horizon coding agents: cross-session project memory (ContextDB), adaptive workflow routing, multi-agent teams, resumable overnight runs, and verifiable evidence — on top of Codex CLI, Claude Code, Gemini CLI, OpenCode, Hermes, Grok, WorkBuddy, Pi, ZCode, and Qoder.
git clone https://github.com/rexleimo/aios.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.