agent-memory — independent software & tools
-
geode
Geode provides agents remote access to your Obsidian vault.
-
session-recall
Shared memory for Claude Code and Codex. Your agent recalls decisions from weeks ago — including what the other engine worked out. Local semantic search over both histories, as MCP tools.
-
qarinah
Your project remembers across coding agents. Compact, cited project memory for Codex, Claude Code, Cursor, and compatible tools.
-
nahuali
Self-inspecting, auditable memory for AI agents: it surfaces the evidence, provenance, and health behind each recall so callers can see which memory to trust. Optional Ed25519-signed tamper-evident ledger. Local-first, Rust.
-
ai-raccoon
Give AI agents a memory that outlives the session: local-first SQLite per project, hybrid search, workspace sandboxes, and optional cloud sync.
-
exomem
Self-hosted MCP server that makes your Obsidian/markdown vault searchable — text, PDFs, Office docs, images, audio — from any MCP client. Hybrid retrieval over a typed, governed corpus, sub-second at 50k notes; your files stay plain markdown.
-
akashic-aurora
Memory for AI agents that learns what actually helped: lessons injected at the moment of action, credited by outcome, challenged by counter-evidence. Local-first, multi-agent, test-gated.
-
loomdb
An agent-native database. Sessions are branches an agent can fork, merge, and rewind; every write records what it was derived from; and taint-and-recall tells you exactly what a poisoned input contaminated. Built on substrate.
-
gnosis
Gnosis is a Greek noun meaning "knowledge" or "awareness"
-
db.md
Your database is a folder of markdown files, and the agent is the engine. The open standard for databases in plain files. No vector store, ever.
-
wavemind
Local-first dynamic memory for agents and apps: SQLite source of truth, vector search candidates, hotness, decay, TTL, namespaces, and benchmarks.
-
forgekit
One config for every AI coding agent — cross-tool config + a cognitive substrate (memory, blast-radius, guardrails) for Claude Code, Codex, Cursor, Gemini, Aider, and more.
-
knowl
Knowledge Operating System for AI agents
-
berimor
Детерминированная агентная архитектура: спецификации, ADR, roadmap и скелет реализации (Rust + TypeScript bootstrap)
-
agent-memory
Agent Memory is a project-local Workspace Memory for AI coding agents. It is a small set of versioned Markdown files in `.agents/memory/`, so work continues across sessions, tools, local, cloud and teammates without chat history and without external infrastructure (no server, vector DB, or embeddings).
-
cogo
COGO — la memoria con semáforo de confianza para construir software con IA. Suite Escriba.
-
owledge
Markdown-first persistent memory and project planning for AI agents, existing knowledgebases, and multi-agent workflows.
-
DeepLaw
DeepLaw 2.0：本地优先单用户 Agent Knowledge OS，融合自主长期记忆、Markdown-native 知识、可信 Ledger、有界上下文与可验证法律证据。
-
mwe-mcp
Persistent, structured memory for AI agents — a human-readable Markdown wiki, multi-user with per-fragment ACL, self-organizing overnight. Agent-agnostic via MCP. Self-hosted, AGPL.
-
agent-hop
Search all your coding-agent chats, then resume any session in any agent.
-
kb
A knowledge base for coding agents, built from Markdown, backlinks, semantic search, and Git context.
-
cc-skills
Build reusable AI agent skills for marketing and engineering tasks with on-demand, domain-specific guidance.
-
io-harness
An embeddable agent runtime for Rust. Any task, any provider, in your process — with a permission boundary, a sandbox, and a durable trace you own.
-
JanexAgent
The agent that grows with you 330+ SKILLS
-
llm-wiki-cli
An agent-first CLI for building persistent, source-grounded wikis from local documents, powered by Rust and SQLite.
-
subfloor
Forkable shell substrate for a single code repository — DB-backed identity, memory, roadmap, content; harness-agnostic boot. We build the data layer, we rent the harness.
-
memory-seed
Portable local memory system and MCP search tooling for file-reading AI coding agents.
-
lemory
🍋 Local-first memory middleware for your Markdown — turn your Obsidian vault into memory for any AI (MCP), with Korean-first hybrid retrieval, keyless on-device search, and an interactive knowledge graph.
-
cc-harness-skills
Package portable CC coding-agent skills for Claude Code, Codex, and OpenClaw with reusable prompts, helper scripts, and installable SKILL.md bundles
-
mnemos
Self-hosted memory + evidence layer for AI agents (Claude Code, Codex, Hermes, ...) — embeddable Go library, MCP / HTTP / CLI, evidence-backed claims, bitemporal recall, axi-go execution kernel with JSONL audit + token budgets, cosign-signed releases with SLSA L3 provenance. No vendor cloud, no per-call billing.
-
kybase
Self-hosted memory for Claude — markdown knowledge base with wikilink graph, hybrid semantic search (pgvector + Ollama), and a first-party MCP server. One docker compose up.
-
memroos
MemroOS / memroos: memory OS and governance layer for AI agents, agent workflows, dispatch, proof, and context continuity.
-
Lians
Agent memory for regulated environments. Bitemporal model, tamper-evident audit chain, GDPR crypto-shred.
-
osk-system
Source-grounded MCP memory runtime and Obsidian-compatible vault template for LLM agents.
-
never-ask-twice
Enterprise Support MemoryAgent on Qwen Cloud that remembers customer context across sessions and proves it with a live re-ask-rate ablation.
-
NeXgen-Engine
Configure your AI coding CLIs from one Git repo you can diff and revert: author AGENTS.md, MCP config, and Markdown memory once, render them to each tool's native format, check for drift, and sync across machines fail-closed. Linux stable, Windows beta.
-
commitlore
Git-native decision memory for Claude Code, Codex, Cursor and other coding agents. Preserve constraints and rejected alternatives; surface only the decisions still in force.
-
agent-infrastructure-landscape
AI agent memory & infrastructure landscape — comparative catalog of 912 systems × 68 columns covering memory layers, agent frameworks, runtimes, vector stores, knowledge graphs, MCP servers, benchmarks. Searchable with typed edges, lineages, citations.
-
ai-brain-starter
The operating system for Claude Code. Memory, accountability, journaling, knowledge graphs, pattern recognition — one install, every session compounds.
-
Syntavra
Adaptive context and runtime optimization for coding agents—reducing token waste, externalizing tool output, preserving exact session history, and enforcing secure tool routing.
-
THOR-memory-bible-for-AI
A memory for your AI coding assistant. It keeps what you tell it and hands the right note back at the moment it matters. Runs entirely on your own machine.
-
qcobrain
Provenance-governed AI memory for agents: a self-evolving second brain in your IDE. Every write cites a source or it's refused. Markdown + grep.
-
tsubasa
Your engineering captain: a repo-resident AI persona with a knowledge graph stored in git. Agents cite incidents, ADRs and PRs instead of guessing — 47% fewer wrong answers, 40% cheaper on a public benchmark. Claude Code plugin + CLI.
-
ResceneAgent
ResceneAgent —— 把前端交付闭环搬进聊天框的本地多 Agent 工作台。一句需求→多 Agent 拆解→流式生成 Vue 代码→真实 Chromium/CDP 预览并亲自点按验收→构建与截图成为交付证据；内嵌编辑器/终端/Diff，AgentFS 隔离快照可回滚，免费模型自动路由。
-
engram
Self-hosted MCP server + dashboard giving Claude Code, Cursor & Hermes agents shared long-term memory over a git-backed markdown vault. Agent-native, Obsidian-compatible second brain — markdown RAG, no vector DB.
-
reelier
Agents make claims. Reelier writes receipts — record an agent's tool-call workflow once, replay it deterministically at 0 tokens, and diff runs to catch drift.
-
memorize
Shared, persistent memory for AI coding agents — Claude Code & Codex share one local-first, event-sourced project brain that survives sessions and syncs across machines. No server, no API key required.
-
amenbo
Task management for AI agents — the record lives outside the AI. Tasks and decisions as connected records in one local SQLite store.
-
second-brain
Persistent memory for Claude Code — the full plugin: hooks, skill, MCP server, workflows. A Markdown vault you own, no server and no account. Hooks-only version: continuum.
-
elite-reasoning-mcp
90+ tool Model Context Protocol server for AI coding agents: workflow flight recorder, quality-gated memory, release doctor, eval harnesses, and reasoning safety.
-
midden
Resolve, audit, visualize, and clean coding-agent context and state.
-
Do-SOUL-Alaya
The local-first memory plane for CLI coding agents. Codex and Claude Code attach via MCP; SQLite-backed, evidence-gated, no GUI. Cross-session memory that the agent proposes and a governance gate decides.
-
NEOTH
Local-first personal AI daemon in Rust — five-tier memory, consent-gated tools, WASM plugin sandbox, multi-provider LLM routing, channels, GUI, signed audit logs, and Babel-Index collapse prediction on its own runtime.
-
theweave
Memory for AI agents you can cat, grep, and git. Markdown-native, MCP-compatible, you own the files.
-
Lumi_Agent
Production-ready autonomous AI agent for software engineering, featuring planning, coding, memory, and continuous self-improvement. OPEN SOURCE.
-
obsidian-memory-kit
An operational prompt that lets an agent set up persistent, cross-device memory for itself using Obsidian MCP and a private GitHub vault on Windows.
-
Veracium
Provenance-aware memory for AI agents.
-
melra
MELRA — Modular Execution Layer for Reliable Autonomy. Open-source durable, policy-governed execution across browser, terminal, files, memory, and computer use—with MCP, CLI, SDKs, and verified evidence.
-
AgentWorkspaceOS
Local-first, Markdown-first operating protocol for shared context, memory, tasks, skills, ownership, and handoffs across Codex, Claude Code, Cursor, and other AI agents.
-
agent-recall-core
Core memory palace engine for AgentRecall