Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
engramory
PromptsAgent 通用长期记忆层:Agent 将重要信息按类型记录为多篇可读的 markdown 记忆文档,文档以链接形式列在限长索引中,索引随会话自动注入。DeepSeek Harness(dsh)有专用插件 dsh-engramory。
git clone https://github.com/tinqiao-oss/engramory.git -
awesome-agent-memory
MCP serversA curated list of memory systems, frameworks, benchmarks, and research for AI agents.
git clone https://github.com/mnemoverse/awesome-agent-memory.git -
animaworks
Agents & frameworksOrganization-as-Code for autonomous AI agents. Brain-inspired memory that grows, consolidates, and forgets. Multi-model (Claude/Codex/Gemini/Cursor/Ollama).
git clone https://github.com/xuiltul/animaworks.git -
Apply LLMs to your data, build personal assistants, and expand your use of LLMs with agents, chains, and memories.
git clone https://github.com/ksm26/LangChain-for-LLM-Application-Development.git -
knowns
Tools & appsTasks, docs, specs and decisions for AI coding agents, as markdown in your repo. Keeps the agent from breaking architectural decisions you already made.
git clone https://github.com/knowns-dev/knowns.git -
In LangChain for LLM Application Development, you will gain essential skills in expanding the use cases and capabilities of language models in application development using the LangChain framework.
git clone https://github.com/Ryota-Kawamura/LangChain-for-LLM-Application-Development.git -
lucid-memory
AI repositoriesMemory 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.
git clone https://github.com/JasonDocton/lucid-memory.git -
renor-engine
MCP serversMemory for coding agents: Markdown notes in a folder, recalled later over MCP. Apache-2.0.
git clone https://github.com/renorai/renor-engine.git -
mnemon
Agents & frameworksLLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime.
git clone https://github.com/mnemon-dev/mnemon.git -
Agent_Memory_Techniques
AI repositoriesAgent memory for LLMs: 30 runnable Jupyter notebooks covering conversation buffers, vector stores, knowledge graphs, episodic and semantic memory, MemGPT, Mem0, Letta, Zep, Graphiti, LoCoMo benchmarks, and production patterns.
git clone https://github.com/NirDiamant/Agent_Memory_Techniques.git -
bosquet
PromptsTooling to build LLM applications: prompt templating and composition, agents, LLM memory, and other instruments for builders of AI applications.
git clone https://github.com/zmedelis/bosquet.git -
openclaw-optimization-guide
Docs & tutorialsMake your OpenClaw AI agent faster, smarter, and cheaper. Speed optimization, memory architecture, context management, model selection, and one-shot development guide.
git clone https://github.com/OnlyTerp/openclaw-optimization-guide.git -
caura
MCP serversCaura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.
git clone https://github.com/caura-ai/caura.git -
MemoSync
Agents & frameworksCo-manage memory with your coding agent across sessions. A local workbench for Claude Code, Codex, Pi and OpenCode.
git clone https://github.com/SLEEPYBQ/MemoSync.git -
memoket-kite
AI repositoriesAn open-source, vector-free long-term memory engine for AI agents, achieving SOTA on LoCoMo and LongMemEval with significantly less context.
git clone https://github.com/memoket/memoket-kite.git -
memlayer
Tools & appsPlug-and-play memory for LLMs in 3 lines of code. Add persistent, intelligent, human-like memory and recall to any model in minutes.
git clone https://github.com/divagr18/memlayer.git -
kaeru
MCP serversCognitive memory for LLM agents — local-first, and shareable across a team through the cloud.
git clone https://github.com/LamantinAI/kaeru.git -
lmc-5
AI repositoriesLiving 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.
git clone https://github.com/wuxuyun0606-collab/lmc-5.git -
claude-brain
SkillsGive Claude Code photographic memory in ONE portable file. No database, no SQLite, no ChromaDB - just a single .mv2 file you can git commit, scp, or share. Native Rust core with sub-ms operations.
git clone https://github.com/memvid/claude-brain.git -
dense-mem
MCP serversSelf-hosted AI agent memory server with MCP, evidence provenance, typed claims, conflict detection, embeddings, recall, PostgreSQL, and pgvector
git clone https://github.com/markhuangai/dense-mem.git -
mentedb
AI repositoriesA cognition aware database engine for AI agent memory. Purpose built in Rust with WAL, HNSW, knowledge graphs, and speculative context pre assembly. Not a wrapper, a ground up storage engine that thinks.
git clone https://github.com/nambok/mentedb.git -
mnemosyne
MCP serversAuditable, local-first memory for AI agents in one SQLite file. MCP server for Claude Code, Cursor and Codex. npm: mnemosy-ai
git clone https://github.com/28naem-del/mnemosyne.git -
dsh-memento
Agents & frameworksBounded, layered, approval-gated, auditable cross-session memory for DeepSeek Harness: a ctx.memory capability seam with a zero-dependency SQLite provider, a memory tool, and frozen snapshot injection. Active (unfrozen 2026-10-12); see README for alternatives.
git clone https://github.com/PerryLink/dsh-memento.git -
iai-personal-memory-engine
MCP serversA cyber brain for your AI. It never forgets a detail, remembers exactly what you said, and learns how you work over time. Free, local, works with Cursor, Claude Code, Codex, OpenClaw, Hermes and more. MIT.
git clone https://github.com/CodeAbra/iai-personal-memory-engine.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.