#embeddings

A capability router for Claude Code — surfaces the most relevant installed skills per prompt via a local hybrid-retrieval hook. Fully local, fail-open.

Offline semantic search engine that runs anywhere.

Composable pre-call and post-call hooks for LLM API calls: pricing, budgets, cost caps, rate limits, event log, observability.

Build backends as typed graphs of operations.

Your tasks with 99% accuracy using any LLM (Claude, DeepSeek, Codex, Gemini, Hermes, OpenClaw, Cursor).

Vector Graph RAG for code & docs with Persistent Chat-Session Memory — BM25 (multi-lang), AST chunking. Hybrid, Compute, Scan, Timeline, Absence, Salience. Graph + temporal knowledge. Privacy Stamps. Source Adapters. Chat summarisation + verbatim copy + free scan. Git indexing. CLI, MCP and Claude Code plugin. Ollama or cloud LLMs. Dashboard.

🚀 Catalyst is a C# Natural Language Processing library built for speed. Inspired by spaCy's design, it brings pre-trained models, out-of-the box support for training word and document embeddings, and flexible entity recognition models.

RAG Skill and MCP for AI agents for codebase indexing and memory

Auditable RAG from the command line: grounded, cited answers over your own documents, with faithfulness verification and retrieval eval you can gate CI on.

No repository description published.

Pinakes — a portable, agent-first knowledge base. One directory = one KB.

local memory tool for your terminal and coding agent

Llama cpp + CapacitorJS support

Persistent, queryable memory for AI agents with intake policy, smart recall, context packs, graph recall, and multi-agent scoping

Python SDK for Aetherfy Vectors — a drop-in replacement for qdrant-client with global sub-50ms latency, built-in analytics, workspace scoping, and client-side payload schema validation.

A second brain for Claude Code: project memory, real token & cost accounting, local semantic recall, and active guardrails.

Local-first RAG server for developers. Semantic + keyword search for code and technical docs. Works with MCP or CLI. Fully private, zero setup.

OpenAPI-generated MCP server for TokenLab text, image, video, music, 3D, audio, files, embeddings, rerank, translation, and async tasks.

No repository description published.

TypeScript and JavaScript bindings for Cortext — npm package @augmem/cortext

Provider-agnostic Go AI framework for building RAG, agents, and AI-powered applications. Swap LLM providers without code changes — supports Ollama, OpenAI, and more.

The only Java AI framework with a complete Dev → Test → Prod prompt lifecycle, featuring multi-agent orchestration and built-in audio processing

A fractal memory plugin and mcp server for opencode.

Token-aware text chunking for RAG - exact source offsets, sentence and markdown modes, zero dependencies.