Runs in isolated Docker or Podman environments; supports browser harnesses and reproducible traces. See the repository and project page for setup and scope.
New
ClawBench is an open-source benchmark framework for evaluating browser and computer-use AI agents on everyday online tasks. It provides reproducible task suites, isolated container runs, browser-action and agent-message traces, screenshots, HTTP interception,…
AI agentsbrowser automationcomputer useevaluationbenchmarksresearch infrastructure
Python 3.11+, tmux (for cookbook), Ollama (easiest for windows)
New
A self-hosted AI workspace -- meant to be the self-hosted version of the UI experience you get from ChatGPT and Claude. But with more jank and fun. Running on your own hardware, with your own data -- local-first, privacy-first, and no trojan.
Works as a local skill, custom instruction package, or project rule. Normal use does not require an API key.
New
An open-source AI coding skill that reviews product and feature risk before agents start building. It helps Codex, Claude Code, Cursor, OpenCode, OpenClaw, and similar tools challenge demand, distribution, pricing, retention, trust, and workflow assumptions…
AI agentscoding agentsproduct validationindie hackersstartupSaaS
Best-supported path: Linux owner machine with tmux, Codex CLI or Claude Code, and Android Chrome PWA / desktop browser through the Faryo Gateway.
New
Faryo is a lightweight phone/desktop workbench for the same tmux-backed Codex, Claude Code, and shell session. It helps developers inspect output, approve actions, send short instructions, and continue long-running AI coding work from a phone without using…
Claude CodeCodex CLItmuxmobileterminaldeveloper tools
Runs as a TypeScript package and MCP server; useful for local agent workflows and server-side formula evaluation.
New
Open-source formula WorkPaper runtime and MCP server for agents and Node services. It lets tools edit cells through an API, recalculate formulas, verify readback, and persist workbook JSON without driving spreadsheet UIs.
Runs on your own machine and orchestrates existing agent CLIs rather than requiring a hosted platform.
New
Ralph Workflow is a free and open-source tool for developers and technical teams who want to orchestrate the coding agents they already use on their own machine. It is built for engineering work that is too big to babysit and too risky to trust blindly: queue…
local AIlocal agentsautomationdeveloper toolsopen sourcecoding agents
macOS app for local Markdown vaults; works well for private notes and AI-assisted knowledge management on Mac.
New
Kuku is an open-source local-first Markdown workspace for macOS. It opens local Markdown vaults, keeps notes as ordinary .md files, and adds personal wiki navigation, backlinks, graph exploration, search, and AI-assisted edits. The assistant proposes changes…
macOS/Linux/Windows via Python CLI; Docker/GHCR available; local-first harness with golden benchmark and regression tests.
New
AI Judge is an open-source AI jury and evaluation harness for catching the gap between smart-sounding model answers and real judgment quality. It combines multi-agent and multi-model council flows, auditable scoring functions, consensus checks, neuro-profile…
LobeHub - an open-source, modern design AI Agent Workspace. Supports multiple AI providers, Knowledge Base (file upload / RAG ), one click install MCP Marketplace and Artifacts / Thinking. One-click FREE deployment of your private AI Agent application.
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
Invoke is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The solution offers an industry leading WebUI, and serves as the…
StableSwarmUI, A Modular Stable Diffusion Web-User-Interface, with an emphasis on making powertools easily accessible, high performance, and extensibility.
The free, Open Source alternative to OpenAI, Claude and others. Self-hosted and local-first. Drop-in replacement for OpenAI, running on consumer-grade hardware. No GPU required. Runs gguf, transformers, diffusers and many more. Features: Generate Text, Audio,…