Havuz

蒸留蔵 — distilled long-term memory for agents: recall by meaning, writing gated by evidence, one kura per agent mode. Ships as a DeepSeek Harn

OwnMem, AI coding agents için proje bilgisini Git deposunda Markdown olarak tutup görevle ilgili içeriği yerel ve deterministik biçimde geri çağıran bir araçtır.

Neden yükseliyor · 42 günde 414 yıldız ve son 28 günde 9 commit, konunun ilgi gördüğünü ve projenin yakın dönemde geliştirildiğini gösteriyor; Git tabanlı ortak bellek ve birden fazla agent entegrasyonu bu ilgiyi açıklayabilir. README'deki benchmark aynı depodaki kilitli CC0 corpus üzerinde yapılmış; gerçek proje çeşitliliğine genellenebileceği ayrıca doğrulanmalı.

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

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 c

Local-first, evidence-aware memory and project continuity for AI coding agents. Checkpoints, context packs and auditable receipts without te

deja-vu, coding agent’ların diskteki geçmiş oturumlarını yerel olarak indeksleyip farklı agent’lardan ortak hafızaya erişmesini sağlayan Go tabanlı bir araçtır.

Neden yükseliyor · 75 günde 1051 yıldıza ulaşması ve son 28 gündeki 794 commit ile dikkat çekiyor; 9 farklı yazarın katkısı da belirgin bir geliştirme hareketliliğine işaret ediyor. Agent’ların zaten diskte bulunan geçmişlerini ortak hafızaya dönüştürme fikri, birden fazla agent kullananlar için somut bir ihtiyaca yanıt veriyor. README’deki benchmark sonuçları proje bakımcısının kendi ölçümleri olduğundan bağımsız doğrulama olarak değerlendirilmemeli.

Gomaa — Autonomous Agent Memory OS. Persistent memory system for AI agents with Obsidian vault integration, hybrid RRF search, knowledge gra

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

Agent-native long-term memory that learns after every run. File-native, auditable, and integrated with Pi, Hermes, OpenCode, and OpenClaw.

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。

Living Memory Coordinate-5: five-axis memory architecture for long-running LLM agents. Minimal SQLite + production PostgreSQL/pgvector refer

Session memory for Claude Code. Auto-captures every session into a plain Obsidian markdown vault. Zero config. MIT. macOS + Linux.

基于本地 RAG 与大模型人格蒸馏的多平台聊天记忆系统。通过 FTS5 检索、语料清洗与长期报告生成，将聊天记录转化为高拟真的数字分身。

Audit trail database for AI agents. Tamper-evident, checksum-backed decision logs with session replay and time-travel debugging to support E

A cyber brain for your AI. It never forgets a detail, remembers exactly what you said, and learns how you work over time. Free, local, works

Agent memory for LLMs: 30 runnable Jupyter notebooks covering conversation buffers, vector stores, knowledge graphs, episodic and semantic m

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

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

Fast, privacy-first desktop & web UI for self-hosted Honcho — browse memories, peers, sessions, conclusions, and chat with memory context.

Self-hosted AI agent memory server with MCP, evidence provenance, typed claims, conflict detection, embeddings, recall, PostgreSQL, and pgve

An "LLM wiki" upgraded to a real database — typed entities, graph relations, HTTP API, and a built-in natural-language agent.

MCP server for external memory layer for AI agents + more . Download from pypi , and get started

The living armor an AI agent inhabits: eternal devouring, eternal evolution, eternal amplification.

Agentic memory for CTI in Python — STIX knowledge graphs, threat-actor alias resolution, offline-first RAG, MCP server for Claude Code and L

Built-in memory decides what to remember. This one asks. Agent memory as plain files in your folder: the agent proposes, you approve, every

Cross-platform persistent memory MCP for Codex, Gemini CLI, Claude Code, and other local MCP hosts. 36 cited neuroscience mechanisms, local-

A local dual-layer memory pattern for AI agents: a compact, human-readable markdown index paired with semantic retrieval from a local vector

Local-first memory layer for LLM apps and agents. Runs offline on Ollama, sentence-transformers and FAISS; OpenAI and Anthropic optional. Im