Explore the directory

A command-line tool that starts a local server exposing an Ollama-compatible API in front of any OpenAI-compatible API, for coding tools that only support Ollama as a custom model provider.

• LLM gateways

A Bun-native orchestration layer that runs on top of a terminal coding agent, dispatching teams of sub-agents to turn a one-sentence brief into finished, audited work.

• Agent frameworks

An MCP server that lets AI agents search DataHub's data catalog, explore lineage and business context, and generate SQL grounded in an organization's real tables, dashboards and documentation.

• MCP servers
• Data engineering

An open-source MCP server that gives coding agents a live, structured index of API vendors, endpoints, sample code and agent-left reviews, so integration decisions are grounded in current data instead of stale training knowledge.

• MCP servers

Downstream tasks and fine-tuning code built on the LucaOne biological foundation model's embeddings, covering protein and nucleic-acid sequence- and token-level classification and regression.

• Models

A Ruby command-line tool and companion website that runs AI language models against code-generation and program-repair benchmarks, then publishes the rankings and metrics.

• AI evals

A local-first command-line tool and terminal UI that crawls a GitHub repository's issues and pull requests, generates embeddings for them, and clusters related work for maintainers to browse.

• RAG
• Git

A native macOS cleaner for developers that scans caches, build artifacts, duplicate files and app remnants, classifies each finding by risk, and explains why it is safe or risky before deleting anything.

• Desktop utilities

An on-device speaker diarization engine from Picovoice that identifies distinct speakers and their speaking intervals in an audio recording, with SDKs for multiple languages and platforms.

• Speech

A Python library that extracts the main content from raw HTML using small encoder models, stripping navigation, ads and boilerplate for feeding cleaned pages to language models or search pipelines.

• RAG

A set of vLLM plugins that serve encoder, pooler and structured-prediction models such as ColBERT, GLiNER and ColPali for production inference, without forking vLLM.

• Inference

A framework-agnostic AI memory system that keeps every extracted fact tied back to an append-only source archive and verifies it before recall. It runs offline on modest hardware with 8 GB or more RAM.

• Agent memory

A set of small practical scripts and task packs for comparing local language models and coding-agent harnesses, measuring raw inference speed, tool-choice reasoning and whether an agent can finish real coding tasks.

• AI evals

A practical, hands-on guide to running large language models and coding agents locally on Apple Silicon, covering inference engine choice, memory sizing, model selection and setting up agent tool calling.

• Inference
• Tutorials

A library of structured skill files that teach an AI coding agent how to write, optimize, debug and port high-performance compute kernels in CUDA, Triton and quantized workloads, rather than guessing at a good approach.

• Agent skills

A local model server for AMD Strix Halo and Radeon GPUs that keeps command-line compatibility with an existing tool while adding day-zero support for newer large mixture-of-experts models and hardware-tuned quantization.

• Inference

A long-term memory plugin for OpenClaw agents that combines exact keyword search over stored facts with vector-based semantic recall, so an agent remembers what a user told it across sessions.

• Agent memory

A VS Code extension that adds a Copilot-style conversational coding assistant in the sidebar, powered by the DeepSeek API, with file editing, code search and shell command tool calls streamed live.

• Coding agents
• Editors

An MCP server that connects an AI agent to structured financial data: wiki articles, research papers, crypto and equity prices, prediction markets, macro indicators and SEC filings, in one configuration.

• MCP servers

A UIKit library for iOS that provides a ready-made chat interface for LLM-powered apps, with streaming responses, tool calling, vision input and speech-to-text built in.

• Agent frameworks
• Mobile

Swift and Python MLX ports of the Hunyuan3D image-to-3D pipeline for Apple Silicon, turning a photo into a textured 3D mesh through separate shape and paint stages, with a bundled command-line tool.

• Generative media

A local MCP server that caches screenshots and UI states using perceptual hashing and vision embeddings, so a coding agent recognizes a screen it has already seen instead of paying for a fresh vision-model call each time.

• MCP servers
• Agent memory

An open-source implementation of Google's TurboQuant method for compressing a language model's key-value cache, with a running summary of which of its variants the community has since found actually work well in practice.

• Inference

A local-first MCP server that gives a coding agent repo memory before it edits: symbols, callers, dependencies, diff-aware review context and decisions pinned to specific commits.

• MCP servers
• Agent memory