Repository Index

Official code for Agent-Reflex: Teaching Language Agents to Act Reflectively

TranslatedOne-click prompt enhancement next to the input box: rewrites a half-finished draft in place into an executable prompt, only rewriting and not sending.

• deepseek-harness
• dsh
• dsh-plugin
• prompt

Uncensored AI API and models — one key for Claude, GPT, Gemini, Grok, DeepSeek, GLM and Kimi, with uncensored and abliterated variants where available. OpenAI- and Anthropic-compatible. Pay per token.

• abliterated-models
• ai-gateway
• anthropic-compatible
• claude-api

TavernGym and TavernBench: a faithful, full-content Hearthstone Battlegrounds simulator with an RL interface, and a 960-task decision benchmark. Code and data for "Build, Don't Play".

• game-ai
• hearthstone
• reinforcement-learning
• rust

StateTrack

Self-hosted web scraper, crawler and document parser for AI agents: URLs, PDFs with OCR and Office files to clean Markdown/JSON. Firecrawl- and Jina-compatible API, MCP server, agent endpoint, Python/Node SDKs. Single Rust binary.

• ai-agents
• browser-automation
• data-extraction
• firecrawl

CaseCite is an open-source, self-hosted legal RAG caselaw research & document analysis platform.

• legal
• legal-ai
• legal-tech
• legaltech

The first exam for code agents in the physical world: frozen robot tasks from many benchmark suites, each answered with a program and verified in a separate sandbox. Runs on Harbor.

• ai-agents
• benchmark
• coding-agents
• embodied-ai

From a universe of models to Collective Model Intelligence.

• collective-model-intelligence
• model-capabilities
• model-collaboration

Official Repository of paper OmniReasoning: Pushing the Limits of Audio-Visual Joint Reasoning

Feather agent harness, training integrations, and evaluation tools for knowledge work

Free AI models for every coding tool — a local OpenAI-compatible gateway for Claude Code, Codex, Cursor, Cline and OpenCode. Based on 9router (MIT).

How many bugs can LMs find & fix in large codebases?

• ai
• ai-agents
• benchmark
• benchmarking

This is the official repo for paper InteractiveWorld A Verifiable Human-Centric Environment for Building Better Interactive MLLM Assistants

MobiInfer runs 35B-A3B-class MoE models fully on-device on the Qualcomm Hexagon NPU, streaming experts from flash with lookahead scheduling (LES) and DSpark speculation.

TranslatedA relay API jailbreak project written in Rust, supporting the Responses / Chat Completions / Anthropic Messages APIs, and supporting most mainstream models such as ChatGPT/Claude/Grok/Gemini/Deepseek/Glm/Kimi

The repository host gives no description.

On-device Vision Model - a fully offline, free vision pipeline that gives text-only models (e.g. DeepSeek) image understanding and multilingual OCR through an OpenAI-compatible local API. Only tokens are needed: no API key, no subscription, no cloud cost. Recommended for native speakers of Chinese, English, Japanese and Korean.

A Hub/research area, for jailbreaking LLM's, and breaking their safety filters.

• ai
• ai-agent
• ai-agents
• ai-jailbreak

TranslatedExamples of bot persona prompts

ModelSphere is an open-source LLM inference infrastructure designed to make production-grade model serving simple, efficient, and continuously optimized.

• ansible
• ascend
• gpu
• helmfile

Official implementation of paper "Cache Engineering for Agents"

PocketStrike is a privacy-first mobile AI workstation. It combines zero-cloud native on-device GGUF inference (ARM NEON accelerated) │ with frontier cloud LLMs, multi-step ReAct agent tools, Model Context Protocol (MCP) servers, self-evolving cross-session memory, and FLUX neural image │ generation.

• agentic-ai
• agents
• ai
• ai-agents

Local multi-AI desktop workspace with official website panels, shared prompts and group collaboration.

• ai-chat
• chinese
• desktop-app
• electron