开发者条目库

A graph-native memory system for AI agents and context graphs. Store conversations, build knowledge graphs, and let your agents learn from their own reasoning —

为超级个体和一个人公司打造一个人的大厂，Hydra九头龙构筑大规模AI调度、数据采集、情报系统、数据平台、分析决策、产品生产的'军事'工业基座。

[ICLR 2026] Tree Search for LLM Agent Reinforcement Learning

提供股票、加密货币的数据查询和分析功能MCP服务器

Stream-Omni is a GPT-4o-like language-vision-speech chatbot that simultaneously supports interaction across various modality combinations.

Local coding agent with neat UI

CLI proxy that reduces LLM token usage by 60-90%. Declarative YAML filters for Claude Code, Cursor, Copilot, Gemini. rtk alternative in Go.

[Fully open] [Encoder-free MLLM] Vision as LoRA

A local, privacy-first résumé builder using LLMs and Markdown to generate ATS-ready DOCX files with Pandoc — no cloud, no tracking.

An AI-powered GitHub code review tool that uses LLMs to detect high-confidence, high-impact issues—such as security vulnerabilities, bugs, and maintainability c

LvLLM is a special NUMA extension of vllm that makes full use of CPU and memory resources, reduces GPU memory requirements, and features an efficient GPU parall

Free-Dall-E-Proxy, an open-source repository that serves as a proxy for API-based interactions with OpenAI's DALL·E 3 image generation model provided by coze.