basic-memory
真正记住的人工智能对话。永远不要再向人工智能重新解释你的项目。加入我们的不和谐:.
这是范围最广的一组:聊天界面、SDK 和框架、提示词与评测工具,以及各种基于大语言模型的应用。很多项目可以接入多家服务商的模型,有些还能在你自己的硬件上运行模型。
打算用在产品里的话,先确认三件事:许可证——有些热门项目限制商用;是否支持你正在用的模型服务商;以及它是否还在维护。每个项目页上的「秒懂」卡片会根据 GitHub 数据回答许可证和维护这两个问题。
真正记住的人工智能对话。永远不要再向人工智能重新解释你的项目。加入我们的不和谐:.
Brigade — Your personal intelligence, built enterprise-grade
Hypergraph is more powerful. Transform unstructured text into structured knowledge with LLMs. Graphs, hypergraphs, and spatio-temporal extractions — with one command.
A Flutter LLM Chat Client. Support Mobile & Desktop.
Cascading runtime for AI agents. Optimize cost, latency, quality, and policy decisions inside the agent loop.
The missing DevTools for Claude Code — inspect session logs, tool calls, token usage, subagents, and context window in a visual UI. Free, open source.
Claraverse is a opesource privacy focused ecosystem to replace ChatGPT, Claude, N8N, ImageGen with your own hosted llm, keys and compute. With desktop, IOS, Android Apps.
Easiest and laziest way for building multi-agent LLMs applications.
中文 NLP 预处理、解析工具包,准确、高效、易用 A Chinese NLP Preprocessing & Parsing Package www.jionlp.com
内存优先、自我改进的代理工具基于 EverOS 构建,具有 MiroThinker 支持的深度研究和推理。
Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs
Datawhale成员整理的面经,内容包括机器学习,CV,NLP,推荐,开发等,欢迎大家star
Portable AI agent runtime for the JVM. One @Agent class runs on Spring AI, LangChain4j, Anthropic, or 9 more behind one SPI. Token streaming, tool calls, human approvals, and governance over WebSocket, SSE, gRPC, or WebTransport/HTTP3. Speaks MCP, A2A, and AG-UI.
🦞 OpenClaw (Clawdbot/Moltbot) 汉化版 - 开源个人 AI 助手中文版 | Claude/ChatGPT LLM 接入 | WhatsApp/Telegram/Discord 多平台 | 每小时自动同步 | CLI + Dashboard 全中文 | 全流程搭建教程,以及排错指南!
XIAOJUSURVEY is an enterprises form builder and analytics platform that allows users to create questionnaires, exams, polls, quizzes, and analyze data online.
A C#/.NET library to run LLM (🦙LLaMA/LLaVA) on your local device efficiently.
控制您的人工智能可以看到的内容。 LeanCTX(精益上下文)是 AI 代理的上下文智能层,这是一种本地 Rust 二进制文件,可以决定它们读取什么、记住它们学到的内容、保护它们接触的内容并证明它们保存的内容。 60 减少 90% 的收据代币。 76 个 MCP 工具,30 多个代理,本地优先。
The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.
SimpleMem: Efficient Lifelong Memory for LLM Agents — Text & Multimodal
High-performance Inference and Deployment Toolkit for LLMs and VLMs based on PaddlePaddle
Power CLI and Workflow manager for LLMs (core package)
大厂发布的AI落地实践、顶尖实验室的最新论文、工业界的真实踩坑记录
Agent Skills as a Memory Layer
Deep dive into Claude Code internals — architecture, agent loop, context engineering, and more. / 深入解析 Claude Code 源码:架构、Agent 循环、上下文工程、工具系统等