Explore the directory

An MCP server, specialized for academic citation analysis, that lets an AI assistant build citation networks from DOIs, calculate author impact metrics such as the h-index, and run graph algorithms like PageRank directly inside a conversation.

• MCP servers

A one-stop NLP platform for small teams that trains, evaluates, and deploys small encoder models such as BERT and BGE, and separately runs blind, human-and-AI-scored prompt evaluations for large model prompts, without fine-tuning large models itself.

• Models
• AI evals

A real-time terminal dashboard, styled like htop, for monitoring an LLM inference cluster running vLLM, SGLang, LMCache, NVIDIA NIM, or NVIDIA Dynamo, auto-discovering pods in Kubernetes with no port-forwarding required.

• Inference
• Monitoring

A library of copy-paste prompts, each defining a specialized autonomous agent for one area of codebase maintenance, security, performance, testing, documentation, databases, and more, meant to be pasted into any AI agent platform for an arbitrary codebase.

• Agent skills

A plugin collection for coding agents, powered by TypeSafe's System One model, that automatically approves harmless shell permission requests in OpenCode and Claude Code while leaving any uncertain request to the agent's normal approval flow.

• Agent skills

A verification-first layer for local LLMs that adds hard test execution, symbolic math checking, and an agentic repair loop on top of a small open-weight model, aiming to match a much larger teacher model's accuracy on checkable tasks.

• Inference
• AI evals

A semantic search engine for the OHDSI medical vocabulary, built as a Rust API and autocomplete service with a React frontend, also reachable as an MCP server for AI agents.

• MCP servers
• RAG

An open-source tool that generates a screen UI specification and an HTML mockup from a plain-language requirements description, using a two-stage LLM pipeline with an intermediate JSON specification to keep screens consistent.

• Design tools

A dynamic, manifest-driven communication framework, the Landmark Manifest Protocol, that lets an autonomous LLM agent discover and call distributed APIs on the fly instead of relying on static, hand-written tool definitions.

• Agent frameworks
• APIs

A hands-on, first-principles course explaining why LLM inference is memory-bound and how techniques such as batching, KV-cache management, quantization, and parallelism address it, with GPU labs building up to vLLM and SGLang.

• Inference
• Tutorials

A local, read-only MCP gateway that aggregates SQLite, MySQL, and PostgreSQL connections behind one endpoint, applying SQL-syntax-tree validation, row and time limits, and a full audit log so an AI agent's database access stays controlled.

• MCP servers
• Databases

A benchmarking framework that measures the real-world runtime performance of GenAI applications such as chatbots, deep research agents, image generation, and live captioning under realistic conditions on consumer-grade hardware.

• AI evals

An MCP server that fuses keyword search, vector embeddings, directory-level summaries, and knowledge-graph expansion into one retrieval tool, giving Claude Code, Copilot, and Cursor a structural understanding of a codebase beyond plain grep.

• MCP servers
• Agent memory

A modular, level-based project template for teams building software with Claude Code, Obsidian, and Figma, letting a team pick a maturity level from a solo copilot setup up to autonomous multi-agent teams with self-healing checks.

• Agent skills

Research infrastructure for AI agents that performs real-time web search with claim-by-claim verification against source pages, returning cited answers with an evidence-based confidence score instead of a model's own self-assessment.

• RAG
• Browser automation

A curated list of tools, frameworks, and guides for running AI models on a user's own hardware without a cloud API, spanning inference engines, quantization, fine-tuning, retrieval, orchestration, and monitoring.

• Inference
• Curated lists

An autonomous AI coding agent that runs inside a Docker sandbox with a persistent shell, a VNC desktop, and parallel tool use, reading a codebase, writing code, running commands, browsing the web, and delegating to sub-agents.

• Coding agents

A specification and skill methodology for Go backend microservices that keeps code and documentation mechanically in sync, so an AI agent can rebuild an entire project from its documentation and skill files alone.

• Agent skills
• Documentation tools

A multi-agent GUI client that lets a developer compare Claude Code, Gemini CLI, OpenCode, and other coding agents side by side, with real-time streaming, session persistence, and searchable history across every agent.

• Coding agents

A TypeScript agent framework that records every read, write, decision, and tool call an agent makes as connected evidence, so a developer can trace a wrong answer back to what the model was given rather than only what the code did.

• AI evals
• Debugging

A production stack for shipping AI agents that wires together existing libraries, LangGraph for the agent graph, LiteLLM for model calls, MCP for tools, and OpenTelemetry for tracing, behind a small, swappable interface.

• Agent frameworks

A peer-to-peer protocol that lets someone serve a private AI skill as a callable remote function over an encrypted channel, so a caller receives only the result and never the underlying prompt, code, or methodology.

• Agent skills
• APIs

A self-hosted cognitive engine that plugs into any language model to give it persistent, tiered memory, a background self-improvement loop, and a runtime self-monitoring layer that watches for and corrects degraded output.

• Agent memory
• AI evals

A persistent memory system for AI agents, backed by SQLite, that combines full-text, trigram, and embedding search across four recall layers, with nightly consolidation, contradiction detection, and encrypted storage for secrets it is given.

• Agent memory