agent-memory
172 servers · 9,529★ total
Local-first AI coding memory for AI agents. Records issues, attempts, fixes and decisions, then warns your agent before it repeats an approach that already failed. Native MCP server for Claude Code, Cursor, Antigravity and Codex. 100% local, no cloud, no telemetry. MIT.
Give your AI agents persistent, collective memory — with deduplicating absorb, supersession lineage, semantic search, and a graph UI. Speaks MCP.
Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Windsurf, Gemini CLI, Antigravity, OpenClaw, Hermes Agent, Oh-my-Pi, Pi, Copilot, Kiro, OpenCode, and Trae.
A 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.
Encrypted, fully offline agentic memory. One click install, GUI w/ memory map, all OS and agents. Superior memory creation, storage and retrieval.
TeleMem is a high-performance drop-in replacement for Mem0, featuring semantic deduplication, long-term dialogue memory, and multimodal video reasoning.
Harness-oriented agent system framework for production-grade LLM agent applications
Portable semantic memory for AI agents: core engine, TypeScript SDK, framework adapters, MCP server, CLI, and host plugins.
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.
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.
Local-first persistent agentic memory powered by Recursive Memory Harness (RMH). Open source must win.
Local, LLM-free memory for AI agents. A single offline Rust binary — deterministic and auditable — that learns from use, forgets the irrelevant, and strengthens what matters. No cloud, no API keys.
Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.
Mine your Claude Code and Codex logs into a local you.md agent profile.
Open-source control plane and runtime for organisational agents: shared company context, isolated execution, approvals and MCP.
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.
Local-first AI memory you can see, edit, and override — portable across Claude Code, Codex, Cursor, Windsurf, and other MCP coding tools.
Persistent session memory for AI coding agents — local-first, with on-device inference, associative recall, and drift detection. Works with Claude Code, Cursor, and Codex.
An agentic memory database that cuts session tokens by 82–99%. One portable SQLite file — your agent's memory, anywhere.
DreamGraph is a graph-governed conceptual development environment (CDE) that turns plans, architecture decisions, and project knowledge into auditable execution through a persistent cognitive graph.
Shared memory MCP server — persistent, searchable, cross-client Claude, Opencode
Shared memory + orchestration for your coding agents — one MCP server, persistent vector memory, agent registry
MCP server with persistent memory + FTS5 search for Claude Code conversation history. Index your ~/.claude/projects/, expose 10 MCP tools, browse via web UI. MIT-licensed.
Repo memory for coding agents. Local-first MCP for Claude Code, Cursor, Windsurf, and Codex CLI: symbol graph, blast radius, diff-aware review, and git-pinned decisions. MIT; no API keys or code upload.
Track work, verify results, carry memory, and sync tools across coding agents. Local files, no daemon.
Biologically-inspired persistent memory engine for Claude Code. 26 cognitive subsystems, Hopfield networks, predictive coding, causal discovery, successor representations, all running locally over SQLite.
Persistent 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.
Outcome-based persistent memory MCP server for Claude Code and OpenCode. Good advice promoted, bad advice demoted. pip install roampal.
Persistent, encrypted memory for AI agents: one Rust binary, one file, no cloud. 122 canonical MCP tools, hybrid recall, bi-temporal history, AES-256-GCM. Local-first, air-gap ready, MIT.
DevContext is a cutting-edge Model Context Protocol (MCP) server designed to provide developers with continuous, project-centric context awareness. Unlike traditional context systems, DevContext continuously learns from and adapts to your development patterns and delivers highly relevant context providing a deeper understanding of your codebase.
Session memory for Claude Code. Auto-captures every session into a plain Obsidian markdown vault. Zero config. MIT. macOS + Linux.
Persistent, local memory for developers and their coding agents. Records commands, output, errors, and the fixes that worked into SQLite and serves them over MCP.
Self-hosted AI agent memory server with MCP, evidence provenance, typed claims, conflict detection, embeddings, recall, PostgreSQL, and pgvector
bhived is an MCP server that gives AI agents shared memory, skills, and tool discovery. install once, works in Claude Code, Cursor, and 15+ other agents.
Live context engine for AI agents: resolve verified workspace state before the context window opens. Pairs with Perseus Vault for persistent encrypted memory. Local-first, MIT. pip install perseus-ctx
The #1 Obsidian MCP for AI memory — freshness-aware, cited, local-first and read-only by default. Dataview, Bases, PDFs, every agent.
Robot Memory - Persistent memory system for AI robots. MCP Server + hybrid search + spatial retrieval.
A runnable reference implementation of multi-agent constraint propagation using MemClaw. 5 specialists share memory via MCP so decisions made upstream automatically govern downstream agents.
The agent harness you steer — structured context, automatic staleness gates, and block-by-block review, all bound to your code. Local-first, MCP-native, open source.
Cognitive memory for LLM agents — local-first, and shareable across a team through the cloud.
Local-first persistent memory for Claude Code & Codex CLI - Rust CLI, hooks, MCP server, SQLite/SQLCipher, auditable recall for long-running coding work.
Agent emotional continuity with PAD state, trust, appraisal, and compact emotion logs.
Persistent cognitive graph memory for AI agents — facts, decisions, reasoning chains, corrections. 16 query types, sub-millisecond. Rust core + Python SDK + MCP server.
Repository-scoped memory for coding agent's decisions, pitfalls, and handoffs stored in one inspectable SQLite file, so agents continue instead of starting over.
Shared memory bus for MCP-compatible agents with permissions, subscriptions, and optional payments.
The open-source safety layer for AI agents — block unsafe tool calls, require approval, enforce budgets, audit, replay.
Give any MCP-capable agent persistent memory: remember/recall over a tiered store with hybrid vector + keyword retrieval. Single Go binary, SQLite or Postgres, embedded admin UI.
AI-first, zero-dependency JavaScript database. Vector search, agent memory, MCP server, and encryption built in. Node.js, Bun, Deno, browsers, and edge runtimes.
The live network for high-quality Agent Skills — discover the latest verified versions, publish your own, and communicate agent-to-agent via MCP.
Relational memory substrate for AI agents with MCP tools, identity continuity, and self-hosted persistence.
Self-hosted Dakera AI memory server — Docker Compose, Kubernetes, Helm, HA cluster setup, and monitoring.
Structured local memory storage and retrieval for LLM agents
Any brain, any agent. Package an AI agent's brain — persona, MCP stack, skills, memory, config — into one open, signed bundle and install it into any framework (OpenClaw, Hermes, Claude Code) in one click.
Persistent AI memory for Claude Code, OpenClaw, and any MCP-compatible agent. BM25F + vector hybrid, governance-aware, local-first, zero-infrastructure.
A TypeScript-based MCP server implementing a memory system inspired by neurodivergent cognitive styles. It organizes thoughts into five districts (knowledge domains), ranks search results using BM25 semantic ranking, and stores memories as a persistent knowledge graph with bidirectional connections.
Local-first agent memory MCP - cross-agent brain with token-saving file diff cache. By Synapse Arrows.
Persistent memory for AI coding tools, in an open portable format. Sync Claude, Cursor, Gemini, Copilot, Windsurf + 6 more across machines via MCP. E2E-encrypted sync. MIT.
The Company Brain your agents install — use your coding agent to run projects and coordinate agents, not just code. Cross-project knowledge graph + immutable audit, self-hosted & EU-resident. BSL 1.1 → Apache 2.0.
MCP-native infrastructure for persistent AI agent memory with encrypted storage, semantic retrieval and cross-agent continuity.
Your coding agent starts every session with amnesia — memo fixes that, 100% on your machine. Persistent memory for Claude Code, Codex, Cursor & any MCP client: Markdown source of truth, hybrid search (MLX/CPU + sqlite-vec), time-machine, contradiction radar, nightly self-optimization. No cloud, no keys.
MCP server in Rust for AI agent persistent memory: branch-aware session handoffs, local ONNX embeddings, SQLite-backed semantic search.
Local-first, eval-first memory for long-horizon AI agents — no LLM at ingest. Python SDK + MCP server with source-traceable recall, belief revision, selective forgetting, and reproducible benchmarks.
Local-first, project-aware memory MCP server for Claude Code, Codex, and other AI agents, with Obsidian and an owner dashboard.
Persistent memory for AI coding agents via MCP — a bitemporal knowledge graph of your codebase, served to Claude Code, Cursor, Gemini CLI, and any MCP client. Tree-sitter + Gemini Flash → Neo4j (via Graphiti). 12 MCP tools, hierarchical clusters, two-regime confidence decay.
Shared, structured memory for AI coding agents — MCP server + CLI. One memory layer for Claude Code, Codex, Cursor & every MCP client.
Agent memory that needs no API key, no LLM, and no embedding provider. One command on Bun and it is serving MCP over stdio against a local SQLite store. Drop-in for the MCP reference memory server. Every memory keeps its source, who may read it, and the evidence that contradicts it.
Local-first memory runtime for AI agents. One command to connect Claude Code, Codex, ChatGPT, MCP workflows, and local agents.
Local-first memory for AI agents: one SQLite file, zero deps. Recency-aware exact recall, conflict detection, time-travel journal, MCP server.
MCP server with 40 tools for AI agents. Memory, web fetch, search, file ops, screenshots, and multi-agent coordination in one Go binary.
AI-first subjectivity kernel for agents — persistent emotional state, relation dynamics, adaptive reply loops. Zero extra LLM calls.
Zero-infrastructure, local-first memory for AI agents. One SQLite file — no Postgres, Neo4j, or cloud. Bi-temporal supersession (updates, never deletes), four-channel hybrid retrieval, and a drop-in MCP server. Runs offline on cheap models. Apache-2.0. Bring your own benchmark.
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.
Living memory for AI agents with an immune system. Episodes compress into identity. Zero dependencies, works with any client.
Build a second brain every AI can share: your content in Oracle AI Database 26ai — semantic search with in-database embeddings, a self-compiling wiki, four kinds of agent memory, and an MCP server that plugs it into Claude, ChatGPT, and any MCP client. Runs on the free local container or Always Free cloud.
Local-first crystalline intelligence for AI agents: the knowledge that endures across sessions, taught as Markdown Domains and captured as Engrams. One Rust binary with MCP server, CLI and hybrid search.
Deterministic, self-hosted long-term memory for AI agents: store facts instead of transcripts, recall only what matters.
Open-source governed memory for AI agents: prompt-injection-resistant writes, purpose-bound retrieval, provenance, and tamper-evident audit.
A memory graph designed for the agent that uses it, not the human who feeds it. Engrama reconstructs context from associations on demand, replacing the "stuff everything into the prompt" reflex with targeted graph traversal. SQLite default, Neo4j optional.
Persistent memory MCP server for Claude Code — self-hosted, n8n + PostgreSQL + pgvector. No cloud required.
MCP-powered memory, policy, and experience layer for safer AI agents.
Persistent memory MCP server for AI agents (MCP + REST)
The continuity layer for everything you do with AI. A self-hosted, open source server any tool plugs into over MCP or REST: hybrid vector + lexical recall, an auto-built knowledge graph, sleep-style consolidation, procedural and persona tiers, OAuth 2.0, multi-tenant. SQLite or Postgres. MIT.
Local-first MCP memory server for AI coding agents with compact retrieval and project/global scopes.
Turns any text stream into a dated history of how its subject changed. Point it at your Claude Code / OpenCode sessions to track how you think and work, or at market news, research notes, or any corpus to track how that changed — raw records to observations to bi-temporal facets to narrative, with provenance, served over MCP. Single pure-Go binary.
A tiny, universal memory engine for humans and AI agents — CLI, HTTP API, MCP server, and shared memory hub in one small Go binary
Vellis — open-source context graph engine for AI agents: typed, local-first memory with explicit schema, validated change, deterministic query, migration, snapshots, replay, and audit. MCP-native. Apache-2.0.
LIFE — Persistent identity architecture for AI agents. 16 MCP servers: drives, heart, memory, patterns, journal, genesis, garden, vision, voice, and more. Zero dependencies. Built across 938 conversations.
Self-hosted MCP server for AI agent memory — 14 core tools, profile-based tiering (86+ available). 88.2% LoCoMo. Works with Claude, Cursor, Windsurf.
Decision memory for AI coding agents. A local-first Go binary and MCP server: records decisions with evidence, scope, provenance and expiry, packs the relevant ones into each agent session within a token budget, and links commits back to the decisions that were in scope when they landed.
dk — CLI for Dakera self-hosted AI agent memory. Manage memories, namespaces, vectors, knowledge graphs, and sessions.
High-fidelity transcript memory for Claude Code — index every session, recall byte-identical, search, prune, compose. Local-first, stdlib-only, MCP.
Go SDK for Dakera AI agent memory — self-hosted, 88.2% LoCoMo. Vectors, hybrid search, knowledge graphs, sessions.
Local-first, audited memory MCP for Claude Code, OpenAI Codex, Gemini CLI, Cursor, Cline, Continue and OpenCode. Your agent gets a navigable cognitive map instead of a bloated context file. Zero cloud. SQLite local storage. Every mutation audited.
The open-source autonomy kernel MELRA — Modular Execution Layer for Reliable Autonomy. An agent-independent effect runtime for governed, durable, and verifiable autonomous execution. MELRA begins where the tool call leaves the model loop.
A cognitive substrate for AI agents — hyperdimensional memory with first-class goals, beliefs, sensory, self-model, and a non-destructive unlearn primitive. Rust top to bottom, embedded-first, no LLM in the read path. One binary, no query language.
Agentic gateway providing persistent LLM memory via a markdown wiki. Open-source core of Kortexio.
Open-source team memory layer for AI coding agents — markdown files in git, user→team→org hierarchy, cross-vendor MCP server. Apache-2.0.
Your cloud knowledge base, in any coding agent — open-source CLI, SDK & MCP server for the Unison brain.
Reliable memory and context infrastructure for AI coding agents: source-backed facts, review-gated learning, MCP/SDK/UI, and replaceable Qdrant/Graphiti retrieval.
Bi-temporal agent long-term memory: SQLite-backed MCP server with recall ranking, hybrid vector+FTS recall, and a source-staleness signal
Local-first MCP memory server for operational project state: decisions, blockers, plans, patterns, and next moves.
Python SDK for Dakera AI agent memory — self-hosted, 88.2% LoCoMo. Vectors, hybrid search, knowledge graphs, sessions.
Durable hybrid memory for AI agents: vector + BM25 + temporal + graph recall, exposed through MCP, HTTP, and Python.
Knowledge engine for AI agents — persistent memory, vault, and brain that learns
Use less context in Claude, Codex, and Cursor. Local AI memory and verifiable work briefs for long-running tasks.
File-first memory runtime for AI agents — versioned, portable, and always there when the next session starts.
MCP server for agent memory over HexxlaDB—ring retrieval, embeddings + lexical search, seams, facets, YAML persistence policy, localhost HTTP transport.
Rust SDK for Dakera AI agent memory — self-hosted, 88.2% LoCoMo. HTTP/gRPC, vectors, hybrid search, knowledge graphs, sessions.
Open source memory infrastructure for AI and humans. Turn scattered knowledge into AI-ready context across Claude, Cursor, ChatGPT, and any MCP client.
Production-backed 6-layer memory architecture for AI coding agents. Model-agnostic — works with Claude Code, Cursor, Aider, Copilot, or any custom agent. Includes templates, scripts, interactive wiki graph builder, and one-line installer.
Tentra MCP — memory for AI coding agents. Persistent code graph + AI architecture diagrams. 32 MCP tools. Works in Cursor, Claude Code, Codex, Windsurf.
Long-term memory for AI agents that stays correct — zero-dependency Python + MCP server for Claude Code. When a fact is corrected, the old value stops coming back.
The knowledge base AI coding agents share. Submit, search, and reuse battle-tested solutions across teams. Self-hosted, MCP-native, AGPL-3.0.
Encrypted memory layer for AI agents, built on Nillion's Blind Computer. MCP server + vault SDK that no operator — not even us — can read.
Persistent memory for Claude Code. Survives compaction and session boundaries: anti-patch reconcile-on-write with LLM-judged de-duplication, a forced PROGRESS.md handoff, a live PLAN.md anchor with an enforced directive ledger, FTS5 search, MCP tools and a GUI. Pure stdlib Python, zero runtime dependencies.
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.
A fully local, zero-config Mem0 memory server for MCP clients on macOS — no LLM, no API key, no cloud. The client is the brain; on-device embeddings + Chroma, auto-managed launchd lifecycle.
Convert AI coding CLI sessions between Codex, Claude Code, Pi, OpenCode, Devin, and Factory. SDK, CLI, MCP chat recall, and trace export for fine-tuning.
An efficiency-first browser-agent system. Fewer observation tokens, lower latency, and browser memory that compounds with every run.
Long-term memory your AI coding agents actually share. One brain, many agents — standalone embedded MCP server: SQLite + FTS5 + vector hybrid search, local ONNX embeddings, self-expiring diary. No server, container, or daemon.
Your coding agent has amnesia and tunnel vision. kyma is the context engine that fixes both — long-term memory plus a live, queryable view of your running system (code, logs, traces), linked by a graph.
MCP that brings persistent agent memory to Kiro, Claude Desktop, Cursor, and any MCP client — powered by agent-memory-daemon 🧠
Zero context compaction for Claude Code & LLM agents. Persistent memory powered by OS primitives (demand paging, kswapd eviction, mlock pinning). Single SQLite file, MCP-native, multi-agent shared.
Persistent memory for AI agents — local, portable, zero config. Works with Cursor, Windsurf, Claude via MCP.
Docker container for centralized Ruflo MCP server with PostgreSQL (RuVector). Architecture: Ruflo (stdio) → Express proxy (Streamable HTTP /mcp).
Shared long-term memory for AI coding agents — one local store for Claude Code, Codex CLI, opencode and anything that speaks MCP. SQLite + FTS5, no vector DB, $1-3/month.
Cross-platform kit that gives AI agents (Claude Code, Codex, Cursor) persistent memory: Markdown vault + git + MCP. Local-first, hybrid search optional.
Persistent institutional shared memory as observable middleware for collaborative AI agents
🧠 Mnema — Long-term memory for AI via MCP × Vector DB. Pluggable backends, hybrid search, Auto Dream consolidation, CLI + REST API + SDK.
Open-source context layer for LLM agents — a single Rust binary served over MCP that feeds Claude, ChatGPT, Codex or any MCP client the facts, decisions & history they need. Local-first, on-device embeddings, hybrid BM25 + vector + graph retrieval. Apache-2.0.
Auditable, self-improving knowledge & memory for AI agents over MCP. Zero-key & multilingual by default · citation-enforced answers · replayable why-trace · judge-gated compounding loop. Postgres-only. Reference implementation of the Agentic Product Standard.
Shared context substrate for AI agents. Retrieval that learns what's useful. Runs local or cloud.
Lightweight persistent memory for AI agents. One SQLite file. Hybrid search. Zero to 12MB.
An AI organism - the human-AI interface layer. A safety reflex that refuses known lethal actions even when the model is fooled, and a memory that only keeps what actually worked. For code, research, writing, or a fleet of agents. 100% local.
Persistent, local-first memory for Claude Code, Codex, Cursor, Gemini CLI, OpenClaw and any MCP agent — cited Markdown, bitemporal history, no hosted account.
Persistent, local-first memory for AI coding agents. Give Claude Code and Cursor memory across sessions over MCP — and see and edit exactly what your AI remembers. Open source, no API key, no cloud.
Local-first memory for AI agents. Stays on your machine, stays yours.
Visibility-aware knowledge network for LLM agents — private+public markdown vault, MCP server, and verified-claims API. Self-hostable.
Thread-scoped runtime contracts for Codex and Claude Code, powered by MCP, local SQLite, Web UI, and UserPromptSubmit hooks
Local-first MCP server for shared memory, reservations, handoffs, and review evidence across AI coding agents.
A human-gated trusted memory ledger for agent systems, with scoped claims, provenance, contradictions, and supersession.
Governed memory for long-lived coding agents. Trust, provenance, conflict detection. Local-first.
PostgreSQL-backed virtual filesystem exposed via MCP tools. Persistent, session-isolated file operations for AI agents.
FlipClaw — Flip the tables. Claude Code CLI is your primary interface. OpenClaw wraps around it with persistent memory, auto-skills, Dreaming, and 24/7 automation.
Persistent identity and memory across AI tools - mcp-native, local-first, framework-agnostic, production-ready.
Self-hostable, open-source shared memory for AI agents: plain markdown in git that a curator agent organizes itself, readable and writable over MCP. Beta — no auth, single machine.
Stop AI agents from confidently using stale facts. MemGuard validates memories in Mem0, Zep, Letta & LangMem against reality — trust scores, quarantine, tamper-proof audit trail, MCP tools. Like Datadog for agent memory.
The persistent home a stateless AI agent can't host for itself — register once, resume your whole self in one call; real browser; cited deep research; hire real humans for physical-world tasks; free keyless chat + ID portraits. MCP + REST, x402 on Base, free to start.
Store and recall robotic experiment data to improve task success by learning from past parameters, trajectories, and outcomes.
MCP-compatible memory governance for AI agents — with structure, state, and lifecycle.
Own your AI memory, don't rent it. A native Claude Code skill AND a standalone, zero-dependency MCP server over one local SQLite file. git clone and go — full-text knowledge graph, plain-markdown, you own the data.
Multi-layer agent memory MCP server — working, episodic, semantic, procedural & affective — for Claude Code and any MCP client.
An open interchange protocol for portable, governable, and auditable memory across AI agents
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.
Open-source agent middleware — shared memory, credential isolation, and schema learning for AI agents. What one agent learns, every agent knows.
Local-first memory engine for AI-agent teams — private/team/project ACL, associative recall, federated sync, and a built-in MCP server. One SQLite file, no LLM required. Apache-2.0.
Persistent engineering memory for coding agents over MCP.
Agent memory system with retain-recall-reflect loop. Hybrid search, entity resolution, observation synthesis. TypeScript library + MCP server.
File-first knowledge base for humans and AI agents — self-hosted Markdown notes with a web editor and a built-in MCP server.
The local-first brain for coding agents: project memory + workflow intelligence + lossless ~50% context savings. MCP server + LLM proxy, zero cloud.
Long-term memory MCP server for AI coding agents. SQLite + FTS5 + vector search, CodeGraph, error learning, compaction survival. Beats Mem0 on benchmarks. No cloud, no API key.
Open-source AI agent memory dashboard and MCP memory template with Supabase pgvector recall, Mem0, Optimization Kit, and Memory File Sync Kit for Claude, ChatGPT, and Cursor.
Local-first shared memory and task coordination for AI coding agents. One Go binary, MCP server, markdown files you own. Hooks for Claude Code and Codex CLI (and their desktop apps).
AI agent knowledge & long-term memory · MCP server, knowledge graph, BM25 + RRF retrieval · drop-in for Claude Code/ Openclaw/ Cursor / Codex / Hermes