Açık kaynak radarı

Havuz

Takip ettiğimiz konularda yükselen açık kaynak projeler — yıldız ivmesi, gerçek geliştirme aktivitesi ve AI değerlendirmesiyle.

repo · sayfa 2 / 2

Sırala

Yıldız/gün (hız)Son gün (★/gün)Son hafta (★/gün)Son ay (★/gün)Toplam yıldız AI önem skoru Bana uyum Commit (28g)Yazar (28g)En yeni

Konu

Tümü AI / LLM18 Veri9 Geliştirici araçları13 Diğer3 SaaS altyapı13 Web11

Süz

Yalnız hareketli Yalnız analizli≥ 0 ≥ 100 ≥ 500 ≥ 2.000

Yalnız hareketli, son 28 günde commit almamış repoları gizler (yıldızı olan ama bırakılmış projeler). Commit sayısı henüz ölçülmemiş repolar da gizlenir.

EtiketTüm GitHub etiketleri — repo sahiplerinin koyduğu topic'lergöster

Sırala:

Etiketler yükleniyor…

Aktif embeddings

51
ailake-io/ai-lakehouse 45
AI-Lake Format: self-contained Parquet + HNSW index — unifying tabular data, embeddings, and vector search in a single Iceberg-compatible fi
0,3/gün ort. +0 son gün — commit Rust 18 May 2026 güncellendi bugün
embeddings hnsw iceberg lakehouse parquet rag rust vector-search
45
52
hopit-ai/Moda 45
MODA: open fashion retrieval benchmark and models by Hopit AI. MODA (203M, open source), MODA Pro Lite (213M, open weights), MODA Pro (hoste
0,2/gün ort. +0 son gün — commit Python 10 Nis 2026 güncellendi 28 Ağu 2026
benchmark clip ecommerce embeddings fashion fashion-clip image-retrieval information-retrieval
45
53
hunhee98/pluck 43
MCP-native code retrieval for AI agents — 84-88% fewer read tokens, BM25F + semantic search, AST chunks, session dedup
0,2/gün ort. +0 son gün — commit Rust 15 May 2026 güncellendi 02 Haz 2026
ai-agents bm25 claude-code cli code-intelligence code-search context-window developer-tools
43
54
aka-kika/the-librarian 42
Skill librarian MCP server — every installed skill costs tokens; the librarian keeps your whole collection out of agent context. Agents ask,
0,4/gün ort. +0 son gün — commit Python 17 Tem 2026 güncellendi 6 gün önce
agent-skills apple-intelligence claude-code embeddings local-first mcp mcp-server ollama
42
55
axem-solutions/shaide 42
Self-hosted, distributed, multi-model LLM inference
0,5/gün ort. +0 son gün — commit Go 13 Ağu 2026 güncellendi 7 gün önce
embeddings enterpise enterpise-ai k8s llms mlops sovereign-ai sovereign-infrastructure
42
56
MADEVAL/FerryAI 42
Native AI inference for PHP 8.3+ - run ONNX, GGUF (llama.cpp) and RubixML models directly in your PHP process via FFI. Chat, streaming, embe
0,3/gün ort. +3 son gün — commit PHP 04 Tem 2026 güncellendi 19 gün önce
ai embeddings ffi generative-ai gguf inference llama-cpp llm
42
57
omermaksutii/mnemo 42
Persistent memory for Claude Code. Your AI never starts from scratch again.
0,2/gün ort. +0 son gün — commit TypeScript 06 May 2026 güncellendi 17 Haz 2026
ai anthropic claude-code embeddings hnsw mcp mcp-server memory
42
58
valpere/session-indexer 42
Per-project semantic search over Claude Code session history. Indexes JSONL transcripts into SQLite; retrieves via bge-m3 embeddings (Ollama
0,3/gün ort. +0 son gün — commit Go 25 Haz 2026 güncellendi 11 gün önce
claude-code cli embeddings golang ollama rag semantic-search session-history
42
59
EngramMemory/engram-memory 39
The highest-scoring AI memory system ever benchmarked that isn't reliant on LLM reranking. And it's free & burns less tokens.
0,2/gün ort. +0 son gün — commit Python 28 Mar 2026 güncellendi 01 Haz 2026
ai ai-tools embedded-systems embedding embedding-vectors mcp mcp-client mcp-server
39
60
markhuangai/dense-mem 39
Self-hosted AI agent memory server with MCP, evidence provenance, typed claims, conflict detection, embeddings, recall, PostgreSQL, and pgve
0,2/gün ort. +0 son gün — commit Go 13 Nis 2026 güncellendi bugün
agent-memory ai-memory conflict-detection docker embeddings golang knowledge-graph llm-memory
39
61
woolcoxm/zero-mem-pi 39
Zero-Mem: Zero-Token Memory Operations for the pi coding agent (faithful reimplementation of arXiv:2607.29377)
0,5/gün ort. +0 son gün — commit TypeScript 13 Ağu 2026 güncellendi 14 Ağu 2026
agents embeddings llm memory pi-coding-agent retrieval-augmented-generation
39
62
Peakstone-Labs/sembr 38
Self-hosted intent radar — Reverse RAG for any input stream.
0,2/gün ort. +0 son gün — commit Python 27 Nis 2026 güncellendi 01 Eyl 2026
bge-m3 embeddings fastapi llm-tools news-monitoring qdrant rss self-hosted
38
63
pvliesdonk/markdown-vault-mcp 38
Generic markdown vault MCP with hybrid search
0,2/gün ort. +1 son gün — commit Python 07 Mar 2026 güncellendi bugün
embeddings fastmcp fts5 knowledge-base markdown mcp mcp-server model-context-protocol
38
64
gambletan/cortex 37
Memory for AI agents that never leaves your device. Local-first, end-to-end-encrypted, zero-telemetry memory engine (Rust, MCP) — gives Clau
0,2/gün ort. +1 son gün — commit Rust 10 Mar 2026 güncellendi 14 gün önce
ai-agents ai-memory bayesian claude embeddings knowledge-graph llm local-first
37
65
rostamlabs/rostam 36
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
0,4/gün ort. +0 son gün — commit Go 10 Ağu 2026 güncellendi 27 Eyl 2026
bm25 database distributed-systems embeddings hnsw hybrid-search key-value-store llm
36
66
jmstajim/NanoTeams 35
Free, open-source AI coding agent & multi-agent teams for macOS — runs 100% on-device via Ollama or LM Studio. Autovisor, an autonomous Supe
0,2/gün ort. +1 son gün — commit Swift 06 Nis 2026 güncellendi 20 Eyl 2026
agentic-workflow ai ai-agents developer-tools lm-studio local-llm multi-agent macos
35
67
GuglielmoCerri/khazad 34
Transparent, transport-layer semantic cache for LLM API calls, powered by Redis 8 Vector Sets.
0,2/gün ort. +0 son gün — commit Python 13 Haz 2026 güncellendi 10 Tem 2026
anthropic embeddings gemini llm openai python redis semantic-cache
34
68
ohdearquant/khive 34
khive is a system of records and operations for agent-native organizations
0,2/gün ort. +0 son gün — commit Rust 07 Haz 2026 güncellendi bugün
ai-agents context-engineering harness knowledge-graph rust sparql mcp embeddings
34
69
jcartu/rasputin-memory 33
The ultimate memory backend for OpenClaw and Claude Code. Persistent conversation memory with LLM fact extraction, foundation-model rerankin
0,1/gün ort. +0 son gün — commit Python 26 Mar 2026 güncellendi 25 Nis 2026
ai knowledge-graph llm memory nvidia qdrant rag self-hosted
33
70
townsendmerino/ken 33
Fast hybrid code search for agents. Pure Go, drop-in MCP-compatible with semble.
0,2/gün ort. +0 son gün — commit Go 19 May 2026 güncellendi dün
agents bm25 code-search embeddings go golang mcp mcp-server
33
71
ashishpatel26/omnicache-ai 31
Unified multi-layer caching library for AI/agent pipelines — LangChain, LangGraph, AutoGen, CrewAI, Agno, A2A
0,1/gün ort. +0 son gün — commit Python 21 Mar 2026 güncellendi 04 Haz 2026
agent agno aiagents autogen caching-memory caching-strategies crewai embeddings
31