Havuz

turbovec, TurboQuant ile vektörleri sıkıştırıp Rust ve Python üzerinden arama yapmayı sağlayan yerel bir vector index kütüphanesidir.

Neden yükseliyor · 185 günde 17.245 yıldız almış olması ve bellek tasarrufu ile hızlı yerel arama vaadi dikkat çekiyor. Ancak son 28 günde commit ve farklı yazar sayısı sıfır; bu veriler yükselişin güncel olarak sürdüğünü göstermiyor. README'deki performans karşılaştırmaları proje tarafından bildiriliyor, bağımsız doğrulama bilgisi verilen ölçümlerde yok.

Semble, coding agent’ların bir codebase içindeki ilgili kod parçalarını doğal dil sorgularıyla bulması için yerel çalışan bir code-search kütüphanesi ve aracı sunuyor.

Neden yükseliyor · 174 günde 6.145 yıldıza ulaşması dikkat çekiyor. Coding agent’ların codebase bağlamına erişimi güncel ve yaygınlaşan bir ihtiyaç; yerel çalışma ve MCP entegrasyonu kurulumu kolaylaştırabilir. Son 28 günde 14 commit ve 3 farklı yazar aktivitenin sürdüğünü gösteriyor, ancak README’deki performans ve token tasarrufu ölçümleri proje tarafından sunulan benchmark iddiaları; bağımsız doğrulama bilgisi verilmemiş.

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.

Hivemind turns your traces into reusable skills across agents

Established strong JEV based natural language to SQL performance and well-covered semantic operators for PostgreSQL with optimized cost and

Embedding-based discovery of duplicated logic for projects too large or messy to maintain reliably

Pretrained text classifiers you can run and retrain on CPU

A prior-art search for your code ideas — has this dev tool already been shipped?

Ask questions across your Markdown notes using a fully local Graph RAG engine. Built for Obsidian vaults, works with any folder of Markdown

memX: self-learning, self-maintaining memory plugin for AI agents; native support for claude code, codex, and openclaw

A lightweight CPU only memory approach with ranked retrieval. Simple, yet effective.

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.

Meet JevEmbed — turn embeddings into decisions. Choose, score, and judge with your choice of embedding model.

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

Shared memory for AI coding tools: hybrid search, cited Q&A, harness memory discovery and a built-in Web console. Local index, MCP + HTTP.

Pharos — local-first agentic RAG for your team's document library: multi-format ingest, hybrid retrieval, enterprise ACL, dual HTTP + MCP ex

A Redis-compatable key-value store. Up to 10x faster. Native vector support.

Fast, AI-agent-native code search in Rust — hybrid BM25 + semantic, Tree-sitter AST chunking, dependency & impact analysis. Drop-in replacem

Local-first code intelligence for AI assistants. Turns your codebase into a knowledge graph your AI can query, navigate, and remember. 25 MC

TiyGate is a lightweight gateway for highly available LLM services. 一款致力于提供高可用 LLM 服务的轻量级网关。

Agentic Voice Notes for iPhone and macOS - Rust, Dioxus, LanceDB + RIG + SQLite

Deploy a self-hosted AI stack with Docker Compose: local LLMs, chat, document parsing, embeddings, transcription, text-to-speech and MCP too

Local-first cross-session long-term memory for DeepSeek Harness — 22 narrow tools, hybrid FTS5 + local-vector retrieval, evidence gate, prov

Embedded retrieval library built on Parquet. Fast, efficient, and scalable.

Retrieve by relevance, not resemblance: filter an AI assistant's memories with TypeSafe's Jev

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

Local document Q&A in your terminal — powered by on-device LLMs.

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

Local, git-versioned memory for AI coding agents. No RAG, no Docker, no external service. Capture, compile, recall over a local LLM wiki wit

All Jina AI APIs as Unix CLI commands. Search, read, embed, rerank - with pipes.

Find, connect, rediscover your notes — a local-first second brain for Obsidian. Semantic search with strong Chinese/CJK, relation graphs and

World's fastest and most compact embedded vector database: exact by default, multimodal, local-first, and GPU-accelerated

Chinese AI learning notes and a minimal RAG demo with Sentence-Transformers, BM25, OpenAI-compatible APIs, and retrieval evaluation.

Self-hosted semantic memory for AI agents, served over MCP. Persistent sessions, experience scoring, a graveyard for dead ends and skills co

Self-hosted RAG platform for AI document search across GitHub, Notion, Google Drive, local files, and web sources with citations.

Local code search combining BM25, vector similarity, and cross-encoder reranking. Parses 60+ languages with tree-sitter, runs entirely offli

Self-hosted, distributed, multi-model LLM inference

A modular local AI agent built with Python and Ollama, featuring tool calling, memory, web search, document processing, embeddings, and RAG.

Zero-Mem: Zero-Token Memory Operations for the pi coding agent (faithful reimplementation of arXiv:2607.29377)

Self-hostable RAG platform - document ingestion, embedding, and vector search behind a simple REST API

🧠 Hybrid long-term memory plugin for OpenClaw agents — SQLite+FTS5 for structured facts, LanceDB for semantic recall

Open Source Brain Platform | AI training and inference in Rust

Universal memory runtime for AI agents

Open-source vector database and sub-microsecond key-value store in one Go engine — embed it as a library, run it standalone, or replicate it

Most AI agents forget you the moment the tab closes. Constellation Engine gives them a hippocampus — a living star map with spreading activa

CLI + Local MCP - A shared structured memory store across Claude Code, Cursor, Windsurf, Antigravity, and every MCP client. Semantically que

Production inference for encoder models - ColBERT, GLiNER, ColPali, embeddings etc. - as vLLM plugins for online and in-process deployment

Skill librarian MCP server — every installed skill costs tokens; the librarian keeps your whole collection out of agent context. Agents ask,

Airgapped closed-corpus QA loop: a self-hosted Qwen3.6 agent explores a .zip dataroom under a token budget with local tools