Stars
Autoharness — a self-learning skill layer for Claude Code — distills skills from your real sessions, updates them as you work, and prunes the ones that stop getting used. No daemon, no benchmark.
Rust-native CLI coding agent for hackers — terminal-native, pipe-composable, scrollback-safe. Built because Claude Code chose non-coders.
HRM-Text is a 1B text generation model based on the HRM architecture, strengthened by task completion and latent space reasoning.
An open-source personal learning agent with three-layer memory (learner profile / wiki knowledge base / cross-conversation recall), a proactive scheduler, personal IM channels, and a workspace-scop…
PDF 全文翻译，保留排版双语对照 · 2.4 亿文献检索一键入库 · 文库知识库问答 · AI 精读论文、综述与思维导图 · 列表直显期刊分区 / 中科院 / JCR / 影响因子 · 免插件网页版 app.ai4paper.pro · 适配 Zotero 7–10
「Octoday Hub 星期八具身智能生态社区」聚合论文、项目、课程、工具、数据集、招聘等资源，连接全球开发者、研究者与产业伙伴。
SDAR (Synergy of Diffusion and AutoRegression), a large diffusion language model（1.7B, 4B, 8B, 30B）
A blueprint-driven AutoResearch runtime for orchestrating AI research workflows from idea generation and experiments to paper writing and peer review.
Open-source local AI workspace — advancing on-device inference.
The memory-first, self-improving agent harness built on EverOS, with MiroThinker-powered deep research and reasoning.
Automatic and end-to-end scientific research workflow enabled by OpenClaw. Produces state-of-the-art level research results.
SenseNova-U series: Native Unified Paradigm with NEO-unify from the First Principles
Open-source trust layer for AI agents — cryptographic agent identity (Ed25519), instance-scoped execution tokens, SHA-256 hash-chained audit logging, and enterprise SSO/SCIM federation. The securit…
MemoryBear Equip AI with human-like memory capability
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
Pack and deploy local AI agents for your team in minutes
[NeurIPS 24] PromptFix: You Prompt and We Fix the Photo
从 ROS 1 bag 提取 H.264 相机帧，支持批量解析、LiDAR 时间戳匹配、PNG 导出和本地 Web 界面。
Easy Data Preparation with latest LLMs-based Operators and Pipelines.
Built by DeepSeek, for DeepSeek — a Swift-native macOS coding agent
The official repository for ArGue: Attribute-Guided Prompt Tuning For Vision-Language Models (CVPR 2024)
OpenTalking: An industrial-grade open-source AI digital human framework that supports real-time conversation, private deployment, and pluggable models.
Predicting high-fitness mutations based on protein inverse folding models
An agent capable of self-evolving and dynamically hardening security
AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool governance, traceable delivery, and provider routing for GPT, Claude, DeepSeek, Qwen, …