Havuz

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.

OpenKB, belgeleri LLM'lerle derleyip sorgulanabilir ve birbirine bağlı bir wiki tabanlı knowledge base'e dönüştüren açık kaynaklı bir araçtır.

Neden yükseliyor · 176 günde 4563 yıldıza ulaşması dikkat çekiyor; kalıcı wiki fikri, PageIndex tabanlı retrieval ve Karpathy'nin benzer bir konseptine yapılan atıf görünürlüğünü artırmış olabilir. Ancak son 28 günde commit ve farklı yazar sayısı sıfır; güncel geliştirme ivmesi olduğuna dair veri yok.

Fold look-alike CJK glyphs (Kangxi radicals, CJK radical supplements) so text extracted from PDFs matches again.

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

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

One embedding space for text, image, video, audio, thermal, motion, and touch. Open weights, self-hostable.

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

~97% token reduction for AI coding sessions — zero deps, 38 languages, MCP server

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

Fast, pure-Python full-text indexing and search. Actively maintained continuation of Whoosh / whoosh-reloaded. Install: pip install whoosh3

A Benchmark for Retrieving Papers that Inspire New Research

Local document knowledge base for DeepSeek Harness: library_add/remove/list, hybrid semantic+keyword library_search with diversity re-rankin

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

Portable semantic memory for AI agents: core engine, TypeScript SDK, framework adapters, MCP server, CLI, and host plugins.

Durable, file-based long-term memory for AI agents. Five-package plugin family: SDK, CLI, MCP server, Hermes adapter, and a LangGraph BaseSt

The marketplace for verifiable AI outcomes: state a task, get a fixed price upfront, and Primitive Bench routes across tools to complete it,

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

Retrieval tools for coding agents, no model in the loop: SOTA-competitive files, search, read, code_pack and write_note over the folder your

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

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

Context retrieval engine for AI agents — semantic + lexical search over codebases

Mintlify Index: retrieval engine and MCP server. Install: npx mint index

Declarative Document Indexing (DDI) framework for Python. Define schemas, extract structured indices, search smarter.

Run AI models on Apple Silicon and Raspberry Pi

Bounded, inspectable LLM inference pipelines from declared YAML — runs offline against Ollama or any OpenAI-compatible local server, emittin

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

Fast hybrid code search for agents. Pure Go, drop-in MCP-compatible with semble.

Train linear embedding adapters with triplet loss to align retrieval embeddings with your queries (RAG).

Verification-gated skill routing and self-improvement harness for Hermes-style agent skills

Federated, local-first search for an AI — one query across transcripts, files, knowledge graph, vector store, and the web, fused by trust-we

Reproducible benchmark and reference pipeline for reranked long-term memory retrieval

A lightweight memory engine for AI agents using fuzzy graphs, Hebbian updates, and optional LLM gating.

Long-term memory plugin for DeepSeek Harness (dsh): four-channel retrieval fusion and continuous memory evolution. Memory construction and r

Long-term memory for LLM apps that shows its work: dated facts, as-of answers, supersession, and receipts on every answer. Library, CLI, loc

Canonical memory infrastructure: BM25 recall over trusted files for AI agents.

A verifiable local memory architecture for long-running AI agents

RAGless is a semantic retrieval system that answers questions about your documentation, without using an LLM at runtime.

A 125-task benchmark for knowledge-mediated implicit associations and retrieval blind spots in long-term agent memory.

Regression testing and configuration sweeps for RAG pipelines, with the statistics to know whether a change actually helped.

Fast, daily-updated skill and CLI for arXiv, PubMed, PMC, and policy retrieval

chew through any source into clean datasets! a fast ingestion, RAG & fine-tuning toolkit

Zero-token long-term memory for Claude Code. Indexes your own session transcripts and retrieves evidence deterministically — entity-context

Airtight math tools an AI uses over MCP — 3.7M-theorem search, PSLQ constant ID, OEIS, real Lean kernel checks, applicability checklists. No

Token-native agent memory retrieval for LLMs, without embedding APIs or vector databases.

Agent memory for Claude Code, Cursor, Codex: MCP server + Graph RAG over your Obsidian or markdown notes. Wikilinks are the graph, SQLite th

SearchCLI, Volcengine AI Search hizmetlerini CLI ve installable Viking skills üzerinden agent ve iş sistemlerine bağlar.

Neden yükseliyor · 142 günlük yaşına göre 1184 yıldız ve son 28 günde 21 commit ile görünür ilgi ve yakın dönem aktivitesi var; üç farklı yazar katkısı da hareketliliği destekliyor. README, agent entegrasyonu ve otomasyona uygun CLI akışlarını öne çıkarıyor; yıldızların veya yükselişin kesin nedenini mevcut verilerle doğrulamak mümkün değil.

🧠 Production-grade memory sidecar for AI agents — gbrain + Hindsight + 3-tier recall. Agent-agnostic, battle-tested. | 生产级外挂记忆系统，兼容Hermes/Cl

Your AI agents can't see your files. ctxd connects your cloud data and makes it searchable via API, CLI, or MCP.

agent-memory, AI agent’ların oturumlar arasında belleği koruması için Markdown tabanlı depolama ve yerel ranked retrieval sağlayan bir runtime’dır.

Neden yükseliyor · 26 günlük yaşına karşılık 1214 yıldız ve son 28 günde 146 commit ile 9 farklı yazar, projeye belirgin ilgi ve aktif geliştirme olduğunu gösteriyor. Ancak bu veriler ilginin nedenini veya gerçek kullanım yaygınlığını tek başına açıklamıyor.