Havuz

Local-first AI action assistant for operators: memory, skills, tools, and permission gates to turn work into controlled action.

A memory system for AI agents modeled on human memory: episodic, affective, reconstructive.

llmwiki (Quiz_wiki) — auto-captures your coding-agent sessions (Claude Code / Codex / OpenCode) into a compounding, local-first project wiki

Keep your decisions, projects, and context when you switch between Claude Code, Cursor, opencode, and the rest — one plain-markdown bundle i

Local-first, auditable memory for AI agents, with governed retrieval, delegated context delivery, and verifiable execution evidence. Works w

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

A free, open-source desktop app for getting work done with AI. It shows you what it would remember before it saves anything.

A memory layer for Claude Code that learns as you work. Persistent, per-context memory as plain markdown in your own git repo. No server, no

Cognitive-structured Multimodal Agent (CMA-Harness): a memory-centric agent for long-horizon multimodal understanding, generation, and editi

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

Persistent, local, cross-IDE memory for AI agents — markdown source of truth, LanceDB-powered semantic search, zero cloud dependency

An open-source AI companion that actually remembers you — runs entirely on your own Mac or server. Desktop pet · long-term memory · proactiv

See which apps are actually eating your memory — helper and child processes rolled up into the app that owns them. Zero-dependency Go CLI fo

Dream-briefing for AI coding agents: a cognitive checkpoint at session end, a 'while you were away' briefing at session start.

The brain is a git repo. Memories are markdown files with YAML front-matter, committed like any other file. Git history is the audit tra

Persistent memory for AI coding agents: automatic capture, explainable recall, knowledge consolidation, privacy controls, and portable offli

A new Git tool for researchers and developers to capture experiments and features as reusable semantic units, then let agents reapply, adapt

An open standard for portable, interoperable AI memory across tools, sessions, and devices.

Durable, repo-native project memory for coding agents, without context bloat.

Git for Agent Memory: Copy-On-Write vector branching for embedded multi-agent memory (83x faster, 3000x smaller snapshots)

Synapse — Temporal knowledge graph memory for AI agents. Self-hosted FalkorDB + Graphiti with hippocampus-layer memory management.

A minimal, extensible, agent-native knowledge repository that keeps shared context current and inspectable

Advanced Memory for LLM characters

🦍 Memorilla: Latent Semantic Memory for LLMs

A macOS app to browse and manage the memory files Claude Code keeps for your projects.

A Unified Memory Benchmark Suite for Memory-Augmented Agents

Your whole desktop context — everything you've seen, read, typed, and heard — as a single MCP your agent can use to understand you and how y

클로드코드 대화의 결정·약속·금지를 자동으로 기억하고, 검색·2D/3D 지식그래프·타임라인으로 보여주는 100% 로컬 기억 도구. 내보내기(6종)·가져오기(미리보기·되돌리기)·백업·복원, 의미검색 중단 알림, MCP 7도구 제공. 기억 데이터는 이 P

Database engine for AI agents — write memory, recall by cue, trust sources over chat. Not SQL, vector DB, or mem0.

Stop wasting tokens and re-explaining your project every session. Recall gives Claude Code , Opencode durable memory — entirely offline.

The Universal Cross-Model Episodic Memory Standard. Local-first, project-scoped SQLite engine for Google Antigravity, Claude Code, Cursor, C

Give your AI a real, persistent memory. The open-source system plus templates that turn an Obsidian vault into your AI's working memory. No

Durable, local-first memory for AI coding agents over MCP — zero-dependency, curated & semantically de-duped, you own the data (SQLite + Mar

All your agents. One memory. Layered, versioned long-term memory for LLM agents, shared across Claude Code, Codex, Cursor and more. 让你的所有AI工

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

轻量、自托管的多入口 AI Agent 机器人｜QQ 官方 / OneBot 11 / NapCat / 微信｜Rust｜Memory / RAG / Todo / Tool Calling

AI coding agents forget. They forget across sessions, and they forget across tools. A decision you reached in Claude Code at midnight is inv

A Codex skill that turns 'do everything' into safe scope, defaults, memory, and AI observability.

Persistent memory plugin for OpenCode. Obsidian-style knowledge base that survives across sessions

EvoEmbedding: Evolvable Representations for Long-Context Retrieval and Agentic Memory

Semantic retrieval for AI agents: high-recall memory and code search that cuts coding-agent token usage by nearly 50%

AI Town Portable is a browser-based multi-agent simulation built on Generative Agents, with LLM-driven residents, long-term memory, planning

Zero-infrastructure, local-first memory for AI agents. One SQLite file — no Postgres, Neo4j, or cloud. Bi-temporal supersession (updates, ne

Turn docs into agent-readable knowledge bundles using Open Knowledge Format (OKF)

An external memory for LLMs: a bi-temporal knowledge graph with hybrid (keyword + vector) retrieval and a self-improving reflection loop. Be

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。

Obsidian-powered daily logs, session logs, /prepforreset handoffs, and wiki janitor skills for AI agents.

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

Open-source template for a durable personal AI agent — web chat, Slack, Linear, and long-term memory with user-approved saves. Eve, Nuxt, Be

Open-source Rust TemporalStore for LLM context management, temporal features, and risk control