Explore the directory

A Python implementation of a published method for simulating physical particle dynamics with a transformer, aimed at building a unified model of how particles move under Lagrangian dynamics.

• Libraries
• Papers

A Python library that profiles the execution time of individual PyTorch layers and functions on a CPU, then simulates how those same layers would run and how much energy they would use on a target hardware accelerator profile.

• Models
• Debugging

A self-hosted MCP server that gives an AI agent perception beyond text search: local speech transcription, reading behind a login wall with the user's own credentials, seeing images and video frames, crossing languages, and remembering past findings.

• MCP servers
• RAG

A semantic tool router for MCP that lets an AI model call one small router tool instead of loading a thousand separate tool definitions into its context, indexing every real tool in a local database and searching it at request time.

• MCP servers

An MCP server exposing a precomputed observation database of 23 large language models across 13 architecture families, letting a coding agent ask which internal layers of different models behave alike, without running any of those models itself.

• MCP servers
• Models

A tool that turns a codebase, an OpenAPI spec, a gRPC proto file, a GraphQL schema, or a plain-language brief describing a data source into a complete, working MCP server, without the developer hand-writing the tool definitions.

• MCP servers

A community-contributed benchmark database of language-model speed and code-quality results measured on Apple Silicon Macs, organized by chip generation and configuration so someone can look up expected performance before choosing a model.

• Inference
• AI evals

A free, browser-based calculator, in Korean and English, that estimates which local AI models a given GPU can run, or which GPUs a chosen model needs, along with quantization and speed estimates, with no install, sign-up or server-side processing.

• Inference

A Discord bot and control plane that connects Discord channels and threads to project-bound coding agents such as Kiro CLI or OMP over the Agent Client Protocol, adding tool policy, cron scheduling, audit logging and agent-to-agent messaging.

• Coding agents

An AI-powered auditor that checks an uploaded iOS or Android app package against Apple's and Android's app-store review guidelines before submission, streaming a live report covering safety, performance, business, design, legal and technical issues.

• Testing

A retrieval-augmented generation application for searching environmental, social and governance policy documents, inspecting the citations behind an answer, and producing traceable reports, running with no external infrastructure required.

• RAG

A Java-based AI coding agent runtime offering a command-line tool, a full-screen terminal UI and a single-process web workbench, tracking and letting a developer undo code changes, tool calls, session branches and git state.

• Coding agents

A fully local, Spanish-language voice cloning and text-to-speech web application that turns a short recorded voice sample into speech reading any typed text, with no account, API or audio upload to a remote server.

• Speech

Open-source deep-research infrastructure for AI agents that searches 40 channels, including more than ten Chinese sources, and returns indexed, deduplicated multi-source results while staying decoupled from any specific LLM provider.

• MCP servers
• RAG

A command-line tool that generates Conventional Commit messages from a staged git diff using a local LLM through Ollama or llama-cpp, so no API key or cloud call is needed to write a commit message.

• CLI tools
• Git

A vector database built from scratch in Rust, organized as a workspace of modular crates with pluggable indexers, storage backends, and HTTP, gRPC and terminal clients.

• Databases

A retrieval-augmented generation framework for Swift, providing document loading, chunking, embeddings, vector stores and query synthesis so document search and question answering can be built natively for Linux, macOS and iOS.

• RAG
• Libraries

A drop-in key-value cache compressor for Hugging Face language models that quantizes the cache to 4 bits, cutting its VRAM footprint and restoring inference speed once long-context generation would otherwise start thrashing.

• Inference

A reference implementation of an LLM agent that keeps a large number of tools in a searchable vector-store library rather than listing them all in every prompt, cutting cost and getting around tool-set limits on context or API size.

• Agent frameworks
• RAG

An unofficial MCP server exposing Stockbit market data for the Indonesian stock exchange, including quotes, top movers, orderbook, fundamentals, sentiment and a read-only portfolio view, to Claude, ChatGPT and other MCP clients.

• MCP servers

A Rust port of PixelRAG that searches documents and video by how a page or frame visually looks rather than only by its text, using screenshots of pages turned into visual embeddings and an approximate-nearest-neighbor index.

• RAG
• Databases

An AI coding harness that has an agent write a plan for a code change and wait for the developer's approval before touching any files, then verifies the finished work against CI and a separate reviewer before calling it done.

• Coding agents

A pure C, single-binary inference engine that runs BitNet ternary models and dense GGUF language models on ordinary CPUs, reported several times faster than Microsoft's own bitnet.cpp and a vendor's own llama.cpp fork on the same hardware.

• Inference

An open-source ecosystem of hundreds of small, composable full-stack packages, plus a CLI, an MCP server and a website tool, designed so an AI agent can assemble a working application from them and a developer can export plain, ownable TypeScript.

• MCP servers
• Web frameworks