llm — independent software & tools
-
gaia-skill-tree
Gaia is a living, open registry of every AI agent skill in existence — structured as a leveling skill graph. Basic skills combine into Extras, Extra Skills evolve into Ultimates. Fork it, extend it, PR a fusion. The complete skill frontier of AI agents, mapped and growing.
-
llm-wiki
Build a personal wiki from your files, messages, and bookmarks using an automated LLM pipeline for knowledge management.
-
geml
One format, two readers. People and AI agents now co-write the same document. Legible for people; addressable, verifiable, and versioned for machines. GEML is plain text — organized by one typed block for everything, remembered by a .gemlhistory sidecar.
-
runeflow
Automate your computer with RuneFlow: record clicks and typing, replay workflows, and use anchor-based vision for reliable desktop control
-
allan-mcp-memory-code
Store persistent knowledge graphs for AI coding assistants using a local Docker setup with hybrid search and entity extraction.
-
agentflare
Run AI coding agents efficiently, and coordinate more than one of them. Zero fluff, zero runtime deps.
-
libero
The open-source AI teammate for Slack. Self-hosted, credential-isolated, every tool call audited.
-
langmesh
An open agent harness you can modify — self-hosted, model-agnostic, with a native macOS app.
-
chatgpt-portal
Bridge private web pages to ChatGPT agents using local Chrome snapshots, Markdown conversion, and secure, controlled navigation.
-
core-agent
Reusable Go base agent on the Google ADK — multi-provider (Gemini, Vertex, Claude on Anthropic + Vertex), MCP-native, with AGENTS.md, skills, and permissions wired up.
-
Go7-Workhorse
One desk for every AI subscription you already pay for — Grok, Claude, Codex, Cursor and your own API keys, each under its own login. A model per chat or auto-routed by task; usage per vendor before the bill. Native desktop app for Windows and macOS. MIT.
-
llm-task-tree
Local-first visual task graph that keeps humans and AI agents aligned on goals, progress, reasoning, and the next action.
-
Linnet
🐦 Your personal AI morning briefing — arXiv, HN & GitHub trends, curated overnight and waiting when you wake up.
-
AI-Email-Orchestrator-Suite
AI Email Assistant 2026 🤖 | Smart Inbox Automation & LLM Replies
-
vibestrate
Every vibe-coder needs a CTO! Let Vibestrate supervise your favorite AI models. You name the work - he makes sure it ships!
-
agentprobe
Test, record, and replay AI agents locally and in CI with a private pytest-style framework
-
ai-engineering-production
AI Engineering Roadmap 2026 🚀 | Build & Deploy AI Apps from Scratch
-
nextbrief
A daily brief across every project you own — every claim checked against evidence before it prints.
-
godplans
Plan everything before anything. Single-command AI agent skill that emits a complete, audit-proof, agent-executable master plan (PLAN.mdx) before any code is written. Claude Code, Codex, Cursor, OpenCode, and every Agent Skills client.
-
hara
A coding agent CLI that runs like an engineering org — role routing, plan DAGs, approvals, memory, and a 10-platform chat gateway. Apache-2.0.
-
Eval-Forge
Production-grade open-source LLM evaluation platform with G-Eval, LLM-as-a-Judge, RAG evaluation, and customizable AI evaluation pipelines.
-
index
Map one unfamiliar repo into a self-contained, verified wiki, or a whole workspace into a two-layer atlas of repos, docs, and dependency graphs. Built from file:line evidence, not guesses. Offline, deterministic, zero runtime dependencies, with a native MCP bridge.
-
codexconclave
Build and orchestrate autonomous AI agent teams with a Python framework for structured workflows, observability, and control
-
arc
Local-first AI orchestration runtime: persistent memory, skills, and task/agent orchestration, all on SQLite. No cloud account or API key required.
-
papers_skills
Streamline academic paper reading, reproduction, and innovation discovery with this integrated research workflow skill for your development toolkit.
-
open-mind
Understand any unfamiliar codebase in an afternoon — a local, deterministic, source-traceable knowledge index (glossary · graphs · code search) that never invents what isn't there.
-
hiloop-interceptor
hiloop interceptor wrapper for agent harnesses - captures LLM calls, network traffic, telemetry, and stdio.
-
Aivory
Self-hosted AI chat platform with multi-step tool calls, persistent Python sandbox, RAG, and Deep Research. Supports Claude, GPT, Gemini and any OpenAI-compatible provider.
-
guia-de-programacion-con-ai
Guia de desarrollo y programacion con herramientas de Inteligencia Artificial y LLMS
-
thesmos-governance
AI governance CLI, GitHub Action, VS Code extension & MCP server — 1,075 rules for Claude, Cursor, Copilot, Gemini, Codex.
-
cc-skills
Build reusable AI agent skills for marketing and engineering tasks with on-demand, domain-specific guidance.
-
iterm-agent
A lightweight agent that turns iTerm2 into your intelligent assistant.
-
sigma
Open-source AI coding agent with sandboxed execution, resumable sessions, verified changes, ACP desktop integration, and a multi-provider model gateway.
-
open-model-license-index
Browse license metadata for popular open models, sourced from Hugging Face model cards, tags, and repo files.
-
please
Please: A smarter way to use Git, powered by AI and built on top of the tools you already know.
-
agent-guidance-kit
Approval-gated, project-local guidance and reusable skills for AI coding agents.
-
haven-42
Haven 42 is an evidence-gated, local-first AI workbench for coding, chat, and media on Windows, Linux, and macOS.
-
watchmend
面向 Homelab 和小团队的 AI 运维哨兵：确定性规则告警、只读 LLM 诊断与降噪、可追溯事件面板和多渠道通知。
-
pbx-mcp
MCP server for Asterisk and FreeSWITCH. Lets AI assistants inspect channels, SIP registrations, trunk status and dialplan on a live PBX.
-
zhiyan-evolviq
智衍 EvolvIQ —— 全球首个开源 AI-Native 工业 Agent 平台。25 个工业智能分身覆盖产线·管理·供应链三层（供应链/良率/质量追溯/DFM/OEE/设备预测维护等），支持 MCP 能力联邦、OPC-UA/Modbus/MQTT 工业协议网关与 Neo4j 跨 Agent 知识图谱。Apache-2.0 全开源。
-
Comodor
A coding agent that lives in your terminal and learns the way you correct it. Fix something once and the next answer already obeys.
-
aetherdev
Build a local-first AI developer agent with zero cost, no telemetry, and self-healing workflows for coding tasks.
-
StratumCode
AI coding agent that shows its work — every step visible, every patch approved by you. Build projects brick by brick, stay in control.
-
AIcortex
Give any LLM a private, self-hosted brain on your NAS: categorized memory & skills, your tools, devices, email, calendar & webhooks, an encrypted vault, roles & per-user areas — single-user or multi-user, all through one MCP connector.
-
get-fable
Make the model you already use work more like a frontier model with better planning, persistent context, skills, hooks, failure handling, and verification
-
ai-product-review-analyzer
AI-powered Amazon product review analyzer built with Python, Streamlit, and Groq LLM to generate intelligent summaries, pros, cons, and buying recommendations.
-
io-harness
An embeddable agent runtime for Rust. Any task, any provider, in your process — with a permission boundary, a sandbox, and a durable trace you own.
-
noeta
The server-side runtime for AI agents. Durable & crash-safe (event-sourced), multi-worker scheduling, per-session sandboxing, human-in-the-loop, provider-neutral. Host agents like Claude Code on your own infra — self-hostable, no vendor lock-in.
-
auto-trend
Daily GitHub Trending scraper with LLM-powered structured analysis, auto-published to GitHub Pages.
-
agents-connector
Connect Claude Code, Codex, and Gemini CLI agents through a local message bus to share tasks, chat, and review work in one tmux session.
-
ironclaw
Security-first, self-hosted AI agents - isolation you can prove, not just promise.
-
llm-hallucination-detector
Identify and evaluate hallucinations in LLM outputs using retrieval-augmented verification and semantic entropy scoring.
-
arena-agent
Skainet Bridge — local automation bridge for AI agents: one process, one port. MCP server + client, REST, browser extension, sandboxed exec. Independent project, unaffiliated.
-
takakia
Lightweight command-line AI chat interface optimized for older or low-spec hardware.
-
datasentry
Evidence-driven, local-first AI copilot for data quality. 39 detectors, six-dimension scoring, human-approved repair, drift engine, MCP/REST/CLI, Web UI — Apache-2.0.
-
llm-wiki-cli
An agent-first CLI for building persistent, source-grounded wikis from local documents, powered by Rust and SQLite.
-
jstack
Evidence-driven engineering control plane for AI coding agents. Full Codex workflows, Claude Code MCP preview, bounded goal loops, signed evidence, audits, and fail-closed release gates.
-
wraith
潜伏在终端与桌面里的幽灵 AI 编程 agent「Wraith」· A ghost-themed AI coding agent for terminal & desktop
-
personacli
Local-first personal workspace: write notes, track tasks, chat with an AI that knows your files - all plain Markdown, no cloud.
-
context-kit
4 PCA templates + 5 Claude Code skills — give any AI agent deep personal context. One-command install.