PostTrainBench
Measuring how well CLI agents like Claude Code or Codex CLI can post-train base LLMs on a single H100 GPU in 10 hours
An AI agent is a program that uses a language model to decide what to do next, calls tools such as a browser, a code interpreter or an API, and repeats until the task is done. The projects here range from frameworks for building your own agents to finished agents that write code, browse the web or run business workflows.
Compare three things. Which models it can use: a single provider, or any OpenAI-compatible endpoint including local ones. How it limits what the agent may do: sandboxing, approval steps and permission lists. And whether it keeps memory between steps and sessions. An agent that runs code or shell commands should run in a sandbox, so check that before giving it access to your machine.
Measuring how well CLI agents like Claude Code or Codex CLI can post-train base LLMs on a single H100 GPU in 10 hours
Cli allows AST search, ~40-50% economy tokens. Claude/Codex/Cursor searches (suitable for any AI agent that can use Bash)
Scaling the Horizon, Not the Parameters
Agili 的 AIGC 周刊 - 一个由 Agentic AI Agent 驱动的 AIGC(人工智能生成内容)精选周刊。
CRDT-based offline-first sync for SQLite. Syncs automatically with SQLite Cloud, PostgreSQL, and Supabase. No conflicts, no data loss, no backend to build. For offline-first apps and AI agents.
Persistent project knowledge graph for coding agents. MCP server with semantic search, in-process embeddings, and web explorer.
Agent skill that draws architecture, flowchart, sequence, data-flow and lifecycle diagrams as hand-placed SVG, to one linted house style.
人形机器人运动智能论文、开源项目、产业与求职知识库
Open source web infrastructure for AI. Scrape, crawl, and automate the web, clean markdown, browser sessions, ready for your agents.
Dataset and benchmark for RAG on company internal documents.
Skills for agentic development on Solana
[ICLR 2026] A Framework for LLM-based Multi-Agent Reinforced Training and Inference
Devopness: AI DevOps on your cloud. Deploy apps, infra and CI/CD. Any cloud and any stack, one MCP. Deterministic API, opinionated and fully configurable. No cloud credentials in AI chats. Free plan.
Boss Skill - BMAD 全自动研发流水线(多 Agent 编排)
This repository contains different LLM chatbot projects (RAG, LLM agents, etc.) and well-known techniques for training and fine tuning LLMs.
OpenClaw-inspired autonomous AI agent built entirely in n8n. Adaptive RAG-powered memory, Skills via MCP templates, Expert Agents with delegated sub-agents, proactive task management, media understanding - self-hosted with one setup script
Your own personal AIGC Factory. Any picture. Any reel. The Comfy way. ©️
Giselle: AI App Builder. Open Source.
A structural code search engine for Al agents.
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 — all backed by Neo4j.
🌳 AI-Powered Skill Tree for Lifelong Human Learning. 30+ skills from K-12 to career & social intelligence, built on cognitive science. | 人类养成记:AI 驱动的终身学习技能树
CLAUDE LEAK - Full Claude Leaked Source Code
An active paper-reading skill that reconstructs author reasoning, explains methods mechanistically, stress-tests assumptions, and generates follow-up research ideas.
Daily-updated Top 100 Agent Skills rankings — installs, growth, and social buzz aggregated from skills.sh, ClawHub, Tencent SkillHub, GitHub, X and 10+ communities. Open data (CSV).