Havuz

Open-source coding agents memory. Records issues, attempts, fixes and decisions, then warns your agent before it repeats an approach that al

Durable, searchable memory of your past agent sessions.

Long-term memory for any AI agent. One Rust binary, offline, 98.2% recall@5 on LongMemEval-S. Self-host free or use Uteke Cloud.

Claude Code-style auto-memory plugin for DeepSeek Harness (dsh): typed memory files + MEMORY.md index auto-injected into the system prompt.

Cognitive memory for LLM agents — local-first, and shareable across a team through the cloud.

文件化经验库：让 AI agent 不再重复踩同一个坑。方法论 + 模板 + 可选工具。

Lemmalog, LLM agent’ların belleğini Datalog kurallarıyla temsil edip kaynak izlenebilir ve artımlı biçimde sorgulayan bir Rust motorudur.

Neden yükseliyor · Agent memory ve MCP konularına yönelik ilgiyle örtüşüyor; 31 günlük repo için 324 yıldızın yanı sıra son 28 günde 27 commit ve 4 farklı yazar var. Bu hareketlilik erken geliştirme temposuna işaret ediyor, ancak yükselişin nedenini doğrudan kanıtlamıyor.

Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code · Codex · DeepSeek Harness · Her

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

Self-hosted continuity memory for persistent AI identities across agents, models, and interfaces.

A shared, git-backed wiki your team's AI agents maintain but can't break — Claude Code, Codex, OpenCode and any MCP client.

Memory for coding agents: Markdown notes in a folder, recalled later over MCP. Apache-2.0.

A living local memory layer for your coding agents and AI tools.

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

OpenAI-compatible proxy that keeps LLM agent context small: it injects relevant memories instead of the full chat history (−51% tokens on re

Compartment, farklı AI agents arasında paylaşılan ve yerel olarak şifreli tutulan kalıcı bir memory sunucusudur.

Neden yükseliyor · 69 günde 581 yıldız ve son 28 günde 34 commit, projeye belirgin ilgi ve yakın dönem geliştirme aktivitesi gösteriyor. Farklı agent istemcileriyle entegrasyon ve offline/encrypted yaklaşımı ilgi çekici; ancak yükselişin kesin nedeni mevcut verilerden belirlenemez. Son 28 gündeki 2 farklı yazar, katkının dar bir grupta toplandığını düşündürüyor.

Markdown-first shared memory vault for Claude Code and Codex with SQLite, Zvec, Git, closeout, and audit

Shared memory for AI agents

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

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。

A lightweight embedded database engine that natively fuses vector search, graph, and document-oriented metadata within a single storage kern

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

Long-running fleet orchestration and memory infrastructure for AI agents. Enables persistent context, shared memory, task execution, and gov

Cairn.ink Memory: lightweight cross-session memory for AI agents, with receipts.

Lossless, local, provable memory for AI agents: every Claude Code session kept on your own computer, word for word, compressed and sealed, a

M-flow, bilgiyi katmanlı bir graph yapısında düzenleyip RAG sorgularında kanıt bağlantılarını izleyerek ilgili anı veya bilgi paketlerini bulmayı amaçlayan bir memory engine'dir.

Neden yükseliyor · 180 günde 4509 yıldız, projeye belirgin ilgi olduğunu gösteriyor; agent memory ve Graph RAG alanlarına yönelik ilgi bunun olası bağlamı. Ancak son 28 günde commit ve farklı yazar sayısı sıfır, bu nedenle ilginin güncel geliştirme faaliyetine veya sürdürülebilir benimsemeye dönüştüğü söylenemez; yıldız artışının nedeni de verilen ölçümlerden belirlenemiyor.

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

Open-source memory runtime for AI agents — reproducible, provenance-tagged context bundles instead of query-time retrieval. Apache-2.0, self

An open-source, vector-free long-term memory engine for AI agents, achieving SOTA on LoCoMo and LongMemEval with significantly less context.

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

Comparison of memory systems for agents

An opinionated bootstrap kit for growing a long-lived, personal Hermes agent — memory, character, and a shared workspace.

Help your agent remember what matters. Keep preferences, carry context across sessions, and bring your memory to the next agent.

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

Self-hosted AI companion with a simulated daily life, long-term memory, and consistent-identity selfies. Your keys, your data, your machine.

Shared, persistent memory for AI agents. Self-hosted MCP server with semantic search, vector RAG, and live updates. Works with Claude, Curso

Self-hosted AI memory and MCP coordination for coding agents. Persistent context across repositories and sessions, with knowledge graphs, hy

SkillCorpus, dağınık SKILL.md dosyalarını agent'lar için seçilmiş, aranabilir skill corpus'larına dönüştüren ve retrieval ile evaluation araçları sunan açık kaynak bir altyapıdır.

Neden yükseliyor · Agent'lar için paylaşılan ve göreve göre seçilen skill katmanına ilgi var; repo kısa sürede 667 yıldıza ulaşmış ve son 28 günde 9 commit ile 3 farklı yazar katkı vermiş. README ayrıca birden fazla benchmark'ta iyileşme bildiriyor; bu sonuçları bağımsız olarak doğrulayamıyorum.

Bitterbot - a mesh of agents that turns shared experience into collective capability.

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

The local-first LLM Wiki: open-source knowledge graph builder, RAG knowledge base, and agent memory store. Built on Andrej Karpathy's patter

Harness-oriented agent system framework for production-grade LLM agent applications

TOMC Memory: CPU context compression and task memory for Codex, Claude Code, Cursor, TRAE, WorkBuddy and other MCP clients.

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

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

Cognitive memory database for AI agents — consolidates duplicates, detects contradictions, fades stale memories via temporal decay. Rust, Ap

Local-first AI memory you can see, edit, and override — portable across Claude Code, Codex, Cursor, Windsurf, and other MCP coding tools.

Causal memory layer for AI agents — MCP server that records decision→outcome relationships. Survives compaction.

Turn isolated Claude sessions into a continuous working relationship

Universal memory runtime for AI agents