Open-source projects tagged “llm”

A public collection of Agent Skills: instruction folders with scripts and resources that Claude loads to handle specialized tasks.

An open-source coding and research agent built around a persistent Python REPL, recursive subagents, and self-refining harness state for long-running tasks.

A reference example of a Claude Code project setup, showing CLAUDE.md, hooks, skills, agents, slash commands, MCP servers and GitHub Actions workflows.

A curated Awesome list of resources, patterns, and templates for designing the scaffolding around AI agents: tools, memory, MCP, permissions, evals, and orchestration.

A self-hosted job search pipeline that searches multiple job boards, scores and tailors your CV per role, and tracks applications in one dashboard.

Python SDK client for Nixtla's TimeGPT, a hosted foundation model for time series forecasting and anomaly detection that runs via API.

Two free online books on harness engineering, analyzing how Claude Code and Codex keep AI coding agents bounded and accountable.

A CLI and web dashboard that benchmarks free coding LLMs across many providers and installs the one you pick into your coding tool.

Local-first AI e-book reader for desktop and mobile, with RAG chat, semantic search, highlights, TTS and WebDAV sync.

Companion code repository for the book AI Agents: The Definitive Guide, with Jupyter notebooks covering agent patterns, evaluation, memory, cost and security.

A community-maintained list of AI models, APIs, and tools that can be used without paying, covering free tiers, open-weight models, and local inference tools.

A collection of 419 pre-trained AI models covering vision, speech, NLP, and LLMs, each runnable from a simple CLI with automatic weight download.

An AI-driven penetration testing tool that uses multiple LLM providers to generate payloads and scan web targets for 50+ vulnerability types.

AI-driven penetration testing automation CLI that orchestrates security tools like nmap and nuclei through LLM-planned, step-by-step workflows.

A Claude Code skill set for contract review, risk analysis, NDA and agreement generation, compliance gap checks, and PDF reports.

A desktop workbench for China A-share stock research that combines market data, theme analysis, AI stock research, portfolio review and daily post-market summaries.

Self-hosted enterprise knowledge base that compiles company docs into a wiki and serves it to Claude and other LLMs via an MCP server with department-level access control.

A Chinese-language book documenting the DeepSeek Harness agent framework, based on hands-on runs of its system prompt, default boot config and session logs.

A curated Awesome-style list of platforms, tools, models and tutorials for running large language models locally.

A local reasoning tool where a small model's step-by-step answers are stored as a knowledge graph, all running on your own machine via Ollama.