Explore the directory

A curated, bilingual list of frameworks, tools and resources for building voice AI agents, covering voice activity detection, turn-taking, real-time speech recognition and speech synthesis.

• Speech
• Curated lists

A curated list of Model Context Protocol servers, split between reference implementations that demonstrate the MCP SDKs and production-ready servers maintained by platform providers for real services.

• MCP servers
• Curated lists

Notebook code for building production-oriented retrieval-augmented generation systems with LangGraph orchestration and local Ollama models, aimed at keeping document data and inference on the developer's own machine.

• RAG
• Tutorials

An open-source framework that gives an AI agent a persistent identity and memory stored entirely in local plain-text files, so its history and personality can survive a model change, a vendor shutdown or a wiped machine.

• Agent memory

A community-maintained knowledge base of articles covering the JavaScript stack for frontend, backend, mobile and DevOps development, published from a GitHub repository to the PurpleSchool site weekly.

• Tutorials

A distributed database for OpenTelemetry metrics, logs and traces whose only durable storage is an object store, so a strictly acknowledged write survives the crash of any Ravel process with no write-ahead log or replicated ingest layer.

• Databases
• Monitoring

A Python integration that lets the Haystack framework use Qdrant as its document store, as a drop-in replacement for other vector embedding stores.

• RAG
• Databases

A self-hosted, open-source LangGraph Agent Server that runs on a user's own Postgres and Redis, aiming for drop-in compatibility with existing LangGraph projects and no license key for persistence.

• Agent frameworks
• Hosting

A zero-code AI agent development scaffold for Java built on Spring Boot and Spring AI, letting a developer launch a working agent from a single YAML configuration file with MCP tool calling and built-in observability.

• Agent frameworks

An enterprise desktop application for orchestrating teams of AI agents, adding audit logging, tool-access policies and observability on top of an existing open-source multi-agent chat interface.

• Agent frameworks

A Claude Code plugin that turns Claude into a full-stack SAP ABAP development assistant, connecting through an MCP server to read, create, update and delete ABAP objects directly on an SAP ECC or S/4HANA system.

• MCP servers
• Agent skills

A desktop application that installs, syncs and manages AI agent skills across many coding tools at once, so a skill added in one place propagates to every supported agent instead of being configured separately in each.

• Agent skills
• Desktop utilities

The official implementation of a paper on retrieval-augmented generation that decides when to retrieve based on statistics from the model's pre-training corpus, rather than relying on the model's own, often miscalibrated, internal confidence signals.

• RAG
• Papers

A source-grounded MCP memory runtime for LLM agents that stores knowledge as local Markdown files in an Obsidian-compatible vault, keeping a person's approved knowledge separate from what an agent has only proposed.

• MCP servers
• Agent memory

An open benchmark, harness and set of embedding models for fashion product retrieval, letting a shopper find products from a photo or a plain-language description and measuring results at full catalog scale against other embedding models.

• RAG
• AI evals

A local, Rust and SQLite memory engine for AI pet and companion applications, keeping owner facts, per-relationship memories and shared history on the device and persisting them across restarts, model changes and network loss.

• Agent memory

A collection of playbooks for the RunMaestro.ai agent orchestrator: saved Auto Run configurations that step an AI agent through a sequence of Markdown task documents until an exit condition is met.

• Agent skills

A pair of tools that validate an Open Knowledge Format bundle of Markdown documents and publish it as a static knowledge website, plus an MCP server that lets an AI agent search and use that same bundle directly.

• MCP servers
• Documentation tools

A graph-native code repository, still in public beta, that stores source code, recorded relationships between functions and types, and versioned history as the repository's own state, queryable by a CLI or an MCP server.

• MCP servers
• Git

A Python implementation of a published method that learns the Kalman gain of a Kalman filter directly from data using a transformer, rather than computing it from a hand-derived model of the system.

• Libraries
• Papers

A quantization method for large language models that rotates weights toward a Gaussian distribution before applying optimal centroids, shrinking a model's memory footprint with close to full-precision accuracy.

• Models

A local-first Windows desktop application and read-only MCP server for searching private Markdown, PDF and Tika-backed document collections using a combination of exact text search and semantic vector search.

• MCP servers
• RAG

An Elixir-native library bringing the practical parts of LangChain, LangGraph and Deep Agents to the BEAM virtual machine, so agents, tools and graph workflows run as native Erlang/OTP processes instead of a separate Python service.

• Agent frameworks

A curated, maintained guide to AI coding tools and platforms, organized as a decision guide by skill level and use case rather than a flat alphabetical list.

• Curated lists