Havuz

Swarm intelligence for distributed AI agents. One agent learns, the whole swarm knows. Shared memories, reminders and agent-to-agent message

Turns corrections into Preferences, Project-specific skills, and Shared skills for Claude Code, Codex, and OpenCode.

Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies

30 sec to give your AI agents persistent memory. Reduce 90% token consumption while also maintaining quality.

Mine your Claude Code and Codex logs into a local you.md agent profile.

Turn your Win, Mac or DGX Spark into an AI hotspot. Nightshift races hundreds of attempts overnight and keeps what passes. Plus the open con

Poirot is a deep research agent kernel built for those who care about how agents are architected.

Vault-LD: an open spec for Markdown vaults as linked data. YAML-LD frontmatter + a shared `@context` = an RDF knowledge graph. Prose for hum

A context harness for AI agents: all your scattered context — code, memory, docs, databases, SaaS — in one searchable, browsable, file-like

Persistent, local memory for developers and their coding agents. Records commands, output, errors, and the fixes that worked into SQLite and

Noema long-term memory plugin for DSH: durable, inspectable agent memory with recall tools and a settings page.

[NeurIPS 2026] MedMemoryBench: Benchmarking Agent Memory in Personalized Healthcare.

Brigade Stack: run coding agents anywhere and keep one record of the work. Shared tasks, claims, verification receipts, handoffs, and MCP an

Persistent memory, reflection & safety for AI agents. No vector DB, no embedding server — BM25 + multi-hop retrieval runs in-process. Hosted

Self-hosted memory server for AI agents. Share context across Claude Code, Codex, OpenCode, and ChatGPT over MCP.

Open plain-text file format for AI memory. Your assistant's long-term memory as .dai files on your disk: readable by Claude, GPT, Gemini, Cu

Local-first memory layer for CLI agents. Indexes Claude Code, Codex CLI, Cursor, Antigravity, and Pi sessions into SQLite + FTS5, searchable

Learn to design an LLM wiki from first principles. Used as agent memory. Workshop with 3 exercises, open-source code, video, and slides. No

Give any MCP-capable agent persistent memory: remember/recall over a tiered store with hybrid vector + keyword retrieval. Single Go binary,

Long-term memory for AI agents with no LLM call: an MCP server and Claude Code plugin, plus local-first context compression for LLM apps.

An assistant that learns how each person it talks to actually works. Runs on your Mac, reaches people through iMessage.

Local long-term memory for AI coding agents. Keeps every conversation word for word, costs nothing to save, and is shared by all your agents

The memory your AI should have had from the start. Automatic capture, automatic recall, 100% local. One SQLite file, zero cloud. Works with

Build portable agent teams across models and harnesses, with shared memory, skills, tools, and workflows — then bring them into Codex, Claud

Git-native memory for coding agents. Repo memory before the diff.

Agentic memory infra for AI agents

Agent 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。

Local-first, inspectable memory for coding agents: durable context across sessions and repositories, code-aware recall, bi-temporal history,

Find out what your coding agents already know. Docmancer indexes the memory, rules, and instructions Claude Code, Codex, Cursor, and Gemini

MemPrivacy is a privacy-preserving personalized memory management framework for edge-cloud agents.

A cognition aware database engine for AI agent memory. Purpose built in Rust with WAL, HNSW, knowledge graphs, and speculative context pre a

the agent experience layer · observability + memory for AI coding agents (Claude Code + Codex) · local-first, typed, yours

Production-Grade AI Agent Development Full-Chain Guide: Development, Testing, and Base Framework

Universal memory runtime for AI agents

Recursive Self-Improvement for AI agents and models, helping your agents self-improve with every run

Source-grounded MCP memory runtime and Obsidian-compatible vault template for LLM agents.

EGC gives every AI coding agent the same brain. Shared memory, skills, and live context across Cursor, Claude Code, Copilot, Aider, and 29 A

Memory as state, not search — deterministic, dependency-free memory for AI agents. The memory lives in a Markdown file.

Persistent code memory for AI coding agents, kept in your project on your machine. Gives Claude Code, Cursor, Cline, Hermes-Agent and any MC

DeepSeek Harness (DSH) local-first cross-session project memory: zero bundled runtime deps, bounded cache-friendly Hot Memory, BM25 recall/c

Muffin — one owner-run personal agent: continuity of memory, work and authority across models, tools and surfaces.

Salt encrypts your agent's files and database memories before they leave your machine.

Local memory for Codex. Reuse work across chats without LLM calls to organize it.

Your coding agent starts every session with amnesia — memo fixes that, 100% on your machine. Persistent memory for Claude Code, Codex, Curso

Portable Markdown memory for agents: six MCP tools, local and remote access, Chinese lexical search, and multi-device sync.

Claude Code harness and alternative to context compaction: at 80% context it writes a verified capsule, runs /clear and resumes with persist

An operating harness for repositories maintained by AI coding agents. Memory hierarchy, verification ladder and reusable workflows.

Open-source alternative to LangGraph Platform for TypeScript — self-host your LangGraph.js agents behind the standard Agent Protocol API. Yo

Self-hosted MCP server + dashboard giving Claude Code, Cursor & Hermes agents shared long-term memory over a git-backed markdown vault. Agen

High-fidelity transcript memory for Claude Code — index every session, recall byte-identical, search, prune, compose. Local-first, stdlib-on