The best-benchmarked open-source AI memory system. And it's free.

Tracking Claude Code Usage Limits

Cognitive memory database for AI agents — consolidates duplicates, detects contradictions, fades stale memories via temporal decay. Rust, Apache-2.0, ships as library / MCP server / HTTP cluster.

Portable project memory across Claude Code, Codex and OpenCode, plus token accounting measured from harness transcripts. Local file I/O, no API calls, no telemetry.

Durable, searchable memory of your past agent sessions.

The local-first LLM Wiki: open-source knowledge graph builder, RAG knowledge base, and agent memory store. Built on Andrej Karpathy's pattern. An Obsidian alternative for personal knowledge management, AI second brain, and durable Claude Code / Codex / OpenClaw memory.

ByteRover CLI (brv) - The portable memory layer for autonomous coding agents (formerly Cipher)

A metasearch library that aggregates results from diverse web search services

Aqua, a cli message tool for AI agents

Collective intelligence runtime for AI agents. Knowledge graph + persistent memory.

Agent-driven proactive memory CLI for AI agents — autonomously recall, maintain, and evolve persistent, source-grounded knowledge across sessions.

Your coding agent starts every session blank. Rekal is the memory your team is missing

Compiles AI agent traces and truns them into reusable context.

Local-first AI PKM for coding conversations: import Claude Code/Cursor/Codex, distill notes, semantic search, tag graph, MCP memory.

Agent-native marketing CLI: 76 skills, 6 research/review agents, brand memory that compounds across sessions, and a local Studio dashboard. One npm install, then /cmo in your coding agent.

Kappa Graph — κ(G). A semantic knowledge graph where knowledge has weight. Extracts concepts, measures grounding strength, preserves disagreement, traces everything to source.

Mission control for Claude Code: run many sessions in parallel with multi-account isolation, transcript viewer, cost tracking, and memory dashboards. Windows + macOS (Apple Silicon).

Every past session, subagent, and workflow -- queryable by your agent, browsable by you

[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.

The semantic layer for software engineering: Connect code to meaning, build on understanding

Save or export your private and public Slack messages, threads, files, and users locally without admin privileges.

A Playwright-based Node.js tool that bypasses search engine anti-scraping mechanisms to execute Google searches. Local alternative to SERP APIs with MCP server integration.

Automatically create new skills based on past agent traces

OKF (Open Knowledge Format): Durable, structured memory for AI agents. Author, validate, consume, and maintain portable knowledge bundles through an ecosystem of Skills, MCP, an interactive graph, TUI, CLI, Docker, and a Claude Code plugin. 100% local.