#rag

Turn PDF, DOCX, tables, and figures into citation-ready reusable agent assets and Foam/LightRAG wikis — MCP SDK 2 server plus VS Code extension

Local-first, inspectable memory for coding agents: durable context across sessions and repositories, code-aware recall, bi-temporal history, MCP, and a self-hosted WebUI.

SDK for seamless integration with the Compresr context compression service.

Go SDK for Dakera AI agent memory — self-hosted, 88.2% LoCoMo. Vectors, hybrid search, knowledge graphs, sessions.

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

Persistent memory MCP for AI agents — SQLite, knowledge graph, 13-tool Python MCP + 17-tool BrainBar surface with ToolAnnotations

No repository description published.

No repository description published.

🐙 Drop-in tools that give AI agents reliable, permission-aware access to external systems.

Full Rust port of Python docling

Self-hostable AI agents you can actually leave running — durable crash-resume, governed autonomy, seccomp sandbox, offline-replayable workflows, CI-native eval. Async-Python, YAML-config, multi-provider (OpenAI/Anthropic/Cloudflare), MIT.

Confidential local RAG for your coding agents.

A cognition aware database engine for AI agent memory. Purpose built in Rust with WAL, HNSW, knowledge graphs, and speculative context pre assembly. Not a wrapper, a ground up storage engine that thinks.

The agentic harness for AI coding agents — intelligence is rented, the harness is owned. Runs the full work cycle: intent briefs, bounded RAG context from real code intelligence, persistent memory, preventive guardrails, and performance evals. One CLI + MCP server, SQLite inside. Claude Code, Codex, Gemini CLI, Cursor & OpenCode.

Git-native engineering knowledge platform for AI agents, connecting specifications, decisions, reviews, code, and tests with traceable context. https://deepwiki.com/theurian/theurian

The agent framework where the model never holds the trigger — every consequential action clears your policy first, waits for a human when it matters, and lands on a record you can verify. Build on it, or put it around the agent you already have.

Strip common prompt injection surfaces.

CPersona — persistent memory for AI agents over MCP. One SQLite file you own, hybrid vector + full-text + keyword search, no LLM in the loop, and honest reporting when recall degrades. MIT licensed.

Graph-based tool retrieval for LLM agents — 248 tools → 82% accuracy, 79% fewer tokens. Zero dependencies. OpenAPI / MCP / LangChain.

Workflow engine where ops can yield — same async DAG handles batch jobs and event-driven streaming pipelines (pipecat-style callbot, STT → LLM → TTS). Python frontend, drop-in Rust runtime; 2–3× faster on chains, 10–30× on production workloads. LLMs, agents, RAG, native compute as first-class ops.

Open-source compiler for AI agents. Write one crewhaus.yaml; compile it to a CLI, a Slack bot, and an eval harness from the same spec. Apache-2.0.

.NET RAG document processing library that transforms PDF, DOCX, HWP, and more into optimized chunks via a 5-stage pipeline with Rust-based FFI readers.

Kreuzberg v4 LTS — long-term support for the v4 line (legacy; superseded by xberg for v5+). MIT-licensed.

ReverseMarkdown.Net is a Html to Markdown converter library in C#.

Google NotebookLM over MCP + a local HTTP REST API. Citation-backed Q&A, audio/video/content generation, multi-account rotation. For Claude Code, Codex, Cursor, n8n, Zapier, Make.

🥤 RAGLite is a Python toolkit for Retrieval-Augmented Generation (RAG) with DuckDB or PostgreSQL

Verified experience for AI agents: independently checked, scoped, cited, and reversible.

Encrypted, fully offline agentic memory. One click install, GUI w/ memory map, all OS and agents. Superior memory creation, storage and retrieval.

Persistent memory & RAG engine for AI agents — SQLite + FTS5 + embeddings, multi-stage recall, sleep maintenance, multi-host hooks

The unified database engine: native SQL, vector search (HNSW), and columnar storage in one Rust engine — from an embedded file to a distributed cluster.