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. lucid-memory

    AI repositories

    Memory for AI that works like yours—local, instant, persistent. 13x faster than Pinecone, 5x leaner than RAG. Finds what RAG misses. Zero cloud, zero cost.

    Stale GitHub, JasonDocton 163 ★GPL-3.0Updated 12 days ago

    git clone https://github.com/JasonDocton/lucid-memory.git
  2. TriviumDB

    AI repositories

    A lightweight embedded database engine that natively fuses vector search, graph, and document-oriented metadata within a single storage kernel — ready to use the moment data is written.

    Indexed GitHub, YoKONCy 191 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/YoKONCy/TriviumDB.git
  3. ClawMem

    AI repositories

    On-device memory layer for AI agents. Claude Code, OpenClaw and Hermes. Hooks + MCP server + hybrid RAG search.

    Stale GitHub, yoloshii 212 ★MITUpdated 9 days ago

    git clone https://github.com/yoloshii/ClawMem.git
  4. memoket-kite

    AI repositories

    An open-source, vector-free long-term memory engine for AI agents, achieving SOTA on LoCoMo and LongMemEval with significantly less context.

    Indexed GitHub, memoket 234 ★Apache-2.0Updated 3 days ago

    git clone https://github.com/memoket/memoket-kite.git
  5. StrataGate-AgentMemory

    AI repositories

    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 118 ★MITUpdated today

    git clone https://github.com/diqierjia/StrataGate-AgentMemory.git
  6. lmc-5

    AI repositories

    Living Memory Coordinate-5: five-axis memory architecture for long-running LLM agents. Minimal SQLite + production PostgreSQL/pgvector reference impls, multi-channel recall pipeline, LLM-proposed hippocampus, persona policies, VPS 7×24 deployment shape. Not another vector DB.

    Stale GitHub, wuxuyun0606-collab 151 ★AGPL-3.0Updated 31 days ago

    git clone https://github.com/wuxuyun0606-collab/lmc-5.git
  7. TrueMemory

    AI repositories

    The memory your AI should have had from the start. Automatic capture, automatic recall, 100% local. One SQLite file, zero cloud. Works with Claude Code, Claude CLI, Cursor, Codex CLI, Gemini CLI.

    Stale GitHub, buildingjoshbetter 385 ★AGPL-3.0Updated 19 days ago

    git clone https://github.com/buildingjoshbetter/TrueMemory.git
  8. dna-memory

    AI repositories

    Claude Code / Codex 共用的长期记忆 MCP:本地 Markdown/Obsidian 存储,跨工具记住你的项目与偏好|Local-first shared memory MCP for Claude Code & Codex

    Indexed GitHub, AIPMAndy 103 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/AIPMAndy/dna-memory.git
  9. mengram

    AI repositories

    Human-like memory for AI agents — semantic, episodic & procedural. Experience-driven procedures that learn from failures. Free API, Python & JS SDKs, LangChain, CrewAI & OpenClaw integrations.

    Stale GitHub, alibaizhanov 207 ★Apache-2.0Updated 7 days ago

    git clone https://github.com/alibaizhanov/mengram.git
  10. matryca-plumber

    AI repositories

    Local-first AI daemon for Logseq OG: background semantic indexing, link hygiene, and agent-ready CLI/MCP — edits Markdown on disk (no cloud, no Logseq API). Karpathy LLM-Wiki inspired.

    Indexed GitHub, MarcoPorcellato 103 ★Apache-2.0Updated today

    git clone https://github.com/MarcoPorcellato/matryca-plumber.git
  11. marm-memory

    AI repositories

    Local-first 3-in-1 AI memory layer & MCP server for Claude Code, Codex, Grok, Gemini, VS Code and Cursor. Fuses session history, codebase indexing & concept graphs in SQLite. Enables zero-cloud, privacy-first context & instant recall, supports multi-agent swarms.

    Stale GitHub, Lyellr88 427 ★Apache-2.0Updated 18 days ago

    git clone https://github.com/Lyellr88/marm-memory.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.