Open-source coding agents memory. 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.

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.

Drop-in AI memory layer with 2x faster retrieval and 10x lower cost. Fully compatible with Mem0 API. Migrate in 5 minutes without any code changes. Self-host for free.

The explainable, local-first memory engine for AI agents. One ~9 MB binary fuses vector + graph + columnar under VelesQL; why() returns the evidence path behind every recall. No cloud, no glue code — runs on server, browser, mobile and desktop.

The ultimate memory backend for OpenClaw and Claude Code. Persistent conversation memory with LLM fact extraction, foundation-model reranking, and 77.7% LoCoMo accuracy. MCP native, REST API, self-hosted.

Auditable memory layer for AI agents: zero-LLM-call local ingest (~10ms/msg, air-gapped), matches Mem0 on accuracy at ~1000x lower ingest cost, bi-temporal belief-state, MCP server. Honest LoCoMo/LongMemEval benchmarks. Open source (Apache-2.0).

Lightweight local memory for agents — every dedup, update, and rerank decision inspectable and tunable. 3 dedup detectors × 4 update resolvers × 3 rerank modes · 60+ parameters · 6 prompts replaceable

The only agent memory that gets better over time. Nightly consolidation, active forgetting, salience scoring. 9.01/10 on AMB benchmark. Local-first, Apache 2.0.

A decentralized cooperative memory & research layer for AI agents — collectively and cooperatively learning and advancing as a community.

The associative memory layer for LLM agents — recall by association, not just similarity.

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.

Lightweight, self-hosted-first AI agent memory engine in Rust single binary.

Semantic Memory OS — universal OpenAI-compatible memory proxy for AI agents. Native Rust, ort+ONNX NLI, SurrealDB embedded.

rererecall: persistent memory for AI coding agents. Search every Claude Code, Codex and Cursor chat and share one memory across them, locally over MCP.

四层记忆引擎 (Memory Engine) — 让 Agent 越用越聪明

Local-first, agent-agnostic memory system that closes the agent loop on any AI agent. Watches any agent's transcript directory on disk and distils long sessions into a curated wiki that re-injects into the next turn. Out of the box: hooks for Codex / Claude / Hermes / OpenClaw; SDK + generic watcher CLI for the rest.

Local-first knowledge-graph memory layer for AI agents — what Mem0 charges for: 4-way RRF + L2 maintenance + bilingual classifier, one local SQLite. usearch f16 runs it on $10/year VPS.

Memory API for AI agents — semantic search, Ebbinghaus decay scoring, knowledge graphs, MCP native. Drop-in mem0/Zep alternative. $19/mo vs $249+.

Open-source memory layer for AI agents. One memory of each customer across every channel, agent and vendor: identity resolution, facts with evidence, context in 11 ms, MCP. A self-hostable alternative to Mem0.

Python SDK for Niadra: shared customer memory for every AI agent in a company. Context before the model call, history, tools and MCP.