Explore the directory

An in-memory data store that speaks the Redis wire protocol as a drop-in cache, while adding native vector search, semantic caching of AI answers by meaning, and a built-in MCP server so agents can use it as a tool directly.

• MCP servers
• Databases

A tool for reviewing AI-generated HTML pages, markdown documents and code diffs by leaving comments directly on the artifact, then sending that feedback back into the originating coding agent to act on.

• Coding agents
• Code quality

A reproducibility study measuring llama.cpp speculative decoding for a quantized Qwen3.6-35B model on a single RTX 3090, with re-derived figures, a coverage probe and a public errata of the study's own retracted claims.

• AI evals

A Rust AI inference engine for embedding local large language models in mobile and desktop apps, loading GGUF checkpoints for on-device chat with bindings for Python, Flutter, React Native, Swift and Kotlin.

• Inference

A terminal visualization tool for local LLM inference that labels a streaming response as exact token provenance or plain SSE chunk mode, and colors verified speculative-decoding steps rather than arbitrary transport chunks.

• Inference
• Debugging

A long-horizon agent harness that decomposes an open-ended, multi-hour request into bounded subtasks, verifies each deliverable against the original goal, and compresses execution state into reusable memory.

• Agent frameworks

A Markdown-based governance system for AI pair programming that adds role isolation, persistent dual-layer memory, sixty-six reusable skills and cross-role directives on top of a plain instructions file, with a Python runtime for guarded continuity.

• Agent skills
• Agent memory

A deterministic multi-hop retrieval-augmented generation system that reasons over a plain, append-only dense index instead of a knowledge graph, so it stays current on data that changes daily without any re-indexing pass.

• RAG

A research codebase for fine-tuning, merging and transporting task vectors between vision and language models, including rebasin methods that align independently trained networks before merging them.

• Models

A local-first MCP management center that lets a developer import server connections once and reuse them across Claude Desktop, Cursor, Codex, Zed, VS Code and other MCP clients, with per-client tool trimming and scene profiles.

• MCP servers

A Claude Code plugin that compiles raw research material into an LLM-maintained Obsidian wiki, then answers questions from it at three depth levels and keeps the wiki healthy over time.

• Agent skills
• RAG

A Claude Code plugin that scaffolds, deploys and connects AI agents to SAP Joule over the A2A protocol on BTP Cloud Foundry, supporting TypeScript agents on Express or CAP and Python agents with LangGraph.

• Agent skills

A 27B-parameter open-weight language model, built on Qwen3.8-27B, tuned specifically for everyday writing such as messages and emails, released free for non-commercial use under a CC BY-NC license.

• Models

A terminal-based support-ticket triage agent that classifies incoming tickets across three domains, retrieves answers from a local documentation corpus, and escalates high-risk or ambiguous requests instead of guessing.

• RAG

A Godot 4 editor plugin that adds an agentic AI coding assistant with multi-session chat history, syntax-highlighted streaming markdown, file-context mentions, and one-click apply or undo of generated code changes.

• Coding agents

A Rust framework that builds an AI agent from a single declarative YAML specification, covering state machines, layered tool policy, twelve LLM providers with fallback, and a memory stack, with no code required for common cases.

• Agent frameworks

A 21-day, day-by-day curriculum teaching DevOps engineers to apply large language models and generative AI to their work, covering LLM fundamentals, prompt engineering, RAG, CI/CD, Kubernetes and building production-style AI-assisted projects.

• Tutorials

A native PHP vector database that stores data in binary files on disk rather than in memory, using HNSW indexing for approximate nearest-neighbor search.

• Databases

A remote Nix store server that replaces SSH with gRPC and mTLS, batching path queries and streaming NAR downloads to make nix copy and remote builds faster over high-latency links.

• CI/CD
• Networking

An AWS-native framework that turns large multilingual document collections into knowledge graphs and answers multi-hop questions over them, unifying Microsoft's GraphRAG and LightRAG retrieval methods on Bedrock, Neptune and OpenSearch.

• RAG

A lightweight CLI that lets AI agent runtimes such as Claude and Codex exchange messages through a shared, file-backed communication directory, with dry-run setup and no central daemon required.

• Agent frameworks

A reinforcement-learning framework that trains an LLM to decide, turn by turn, when to reason, whether to retrieve from unstructured text or a knowledge graph, and when to answer, for adaptive hybrid retrieval-augmented generation.

• RAG

A vector database and sub-microsecond key-value store in one Go engine, runnable as a standalone server, a Raft-replicated cluster or an embedded library, with an MCP server for agent memory and an LLM response cache.

• Agent memory
• Databases

An ICML 2026 hierarchical tree-based RAG framework that builds a corpus-level abstract tree index for cross-document retrieval, answering complex queries with a multi-granular agentic retrieval pipeline.

• RAG