Explore the directory

Timeloop is an infrastructure for modeling, mapping and generating code for dense and sparse tensor-algebra workloads on a range of hardware accelerator architectures.

• Languages

A macOS assistant that runs a local language model every night to turn the user's files, messages and screenshots into a private knowledge base, then proactively drafts and finishes tasks the next morning.

• Agent frameworks
• Agent memory

A set of 23 custom plugins for the hermes-agent autonomous agent runtime, covering autonomous decision-making, telemetry, cost control, hallucination and prompt-injection defenses, and adaptive long-term memory.

• Agent skills
• Agent memory

A dataset and benchmark of more than 500,000 simulated company documents and 500 questions for evaluating retrieval-augmented generation systems on realistic enterprise data.

• RAG
• AI evals

A modular Rust implementation of GraphRAG that builds knowledge graphs from documents and answers natural-language questions over them, with server-only, WASM-only and hybrid deployment options and optional GPU acceleration through WebGPU.

• RAG

This project packages vLLM for serving large language models on AMD Ryzen AI Max "Strix Halo" hardware as an Ubuntu-based, Toolbx-compatible Docker or Podman container tracking stable ROCm and vLLM releases.

• Inference
• Containers

A curated collection of tutorials, papers, tools and best practices for fine-tuning large language models such as GPT, BERT and RoBERTa.

• Models
• Curated lists

A Claude Code plugin with 26 specialist agents and enforced coding rules for Elixir, Phoenix and LiveView projects, planning, implementing, reviewing and verifying changes in parallel and integrating with the Tidewave MCP server.

• Agent skills
• Code quality

A terminal-first development environment for coding agents that runs each agent's session in a background daemon so it can be detached, reattached from another device, or run remotely over SSH.

• Coding agents
• Terminals

A headless, library-first Rust SDK for embedding a complete OpenAI coding-agent loop, including retained sessions, typed history, tools, branches and retries, into other products.

• Agent frameworks

A security-operations platform that provides a single interface over open-source security tools such as Wazuh, Graylog, Velociraptor, Grafana and InfluxDB, connected through their own APIs and webhooks.

• Security
• Monitoring

patent is a command-line tool that searches package registries, GitHub and Hacker News for prior art on a plain-English dev-tool idea, then ranks matches by semantic similarity and summarizes the landscape as Open, Crowded or Saturated.

• RAG
• CLI tools

A large collection of specialized agents, skills and hooks that turns Claude Code into a self-learning AI software team, covering planning, building, reviewing, testing and monitoring.

• Coding agents
• Agent skills

A paper collection accompanying a survey on AI-assisted and automated scientific research, organized around the full research lifecycle from idea generation through writing, peer review and dissemination.

• Curated lists
• Papers

A curated list of tools, skills, subagents and plugins for OpenAI Codex CLI, the terminal-based coding agent, organized by category such as MCP servers, IDE integrations, hooks and session management.

• Curated lists

OpenClip is an open-source macOS menu-bar utility that pops up contextual actions for selected text, such as copy, transform, calculation and AI-assisted writing, and supports custom extensions in JavaScript, AppleScript or shell.

• Desktop utilities

A Chinese-language practical guide to ten mainstream AI coding tools, with 66 Claude Code tips, tool-specific best practices, prompt-engineering methodology and copyable configuration templates.

• Tutorials

vLLM Playground is a web interface for running, managing and chatting with vLLM inference servers, supporting GPU and CPU backends including Apple Silicon and OpenShift or Kubernetes deployment.

• Inference

The official command-line interface for Alibaba Cloud's Model Studio (DashScope) AI platform, exposing chat with Qwen, image and video generation and editing, speech synthesis and recognition, and workflow orchestration as structured tool calls for AI agents.

• Generative media
• CLI tools

A platform for hosting, deploying, building and fine-tuning open-source large language models, packaging inference and fine-tuning behind an OpenAI-compatible API and OCI-based model distribution.

• Inference
• Hosting

A data-driven landscape and dataset of agentic AI and model infrastructure projects, tracking GitHub metadata and OpenRank vitality scores, produced by Ant Open Source and inclusionAI.

• Curated lists

A Chinese-language technical book that explains the DeerFlow 2.0 agent framework's architecture and source code in depth, aimed at developers who want to extend or customize it.

• Books

Open-source, governed shared memory for multi-agent, multi-tenant AI fleets, with trust tiers, audit trails, a knowledge graph and self-improving retrieval, formerly named MemClaw.

• Agent memory

lossless-claw-enhanced is a deprecated fork of a context-management plugin for OpenClaw that replaces sliding-window compaction with a DAG-based summarization system preserving every message within the model's token limit.

• Agent memory