Lists (2)
Stars
Standardized tool schemas and SDKs that expose Sciverse Open Platform retrieval capabilities to LLM agents.
Garry's Opinionated OpenClaw/Hermes Agent Brain
Open-source scientific and technical publishing system built on Pandoc.
Eagle: Frontier Vision-Language Models with Data-Centric Strategies
DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.
SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.
《御舆：解码 Agent Harness》42万字拆解 AI Agent 的Harness骨架与神经 —— Claude Code 架构深度剖析，15 章从对话循环到构建你自己的 Agent Harness。在线阅读网站：
[ICLR 2023] ReAct: Synergizing Reasoning and Acting in Language Models
企业级AI Agent的Rust实现，支持沙箱隔离，审计安全，使用统计，钉钉接入等实用功能。
A protocol for connecting any editor to any agent
Open-source, secure environment with real-world tools for enterprise-grade agents.
DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm
Warp is an agentic development environment, born out of the terminal.
A beautiful config generator for Ghostty terminal.
A lightning-fast search engine API bringing AI-powered hybrid search to your sites and applications.
FinGLM: 致力于构建一个开放的、公益的、持久的金融大模型项目，利用开源开放来促进「AI+金融」。
The agent that grows with you
Lightweight, open-source AI agent for your tools, chats, and workflows.
The free build of Claude Code. All telemetry removed, security-prompt guardrails stripped, all experimental features enabled.
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
Distributed Task Queue (development branch)
A one stop repository for generative AI research updates, interview resources, notebooks and much more!
Enterprise RAG Challenge to test accuracy of different LLM-driven assistants
Repository for pre-built dev container images published under mcr.microsoft.com/devcontainers
The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text.
A unified inference and post-training framework for accelerated video generation.
Defines a common protocol for language servers.