Awesome AI Agents › AI Assistants

Companion-Inc/feynman

⭐ 10091 TypeScript added to this list on 2026-09-28 repository created 2026-03-19

Feynman is an open-source command-line AI research agent aimed at scientific and technical research work rather than general coding. It is installed via a shell script on macOS and Linux, a PowerShell script on Windows, or npm, and after installation a `feynman setup` step connects it to a model provider, with support for local models and editor integrations such as Zed. Once configured, a user runs natural-language queries directly (for example asking what is known about a topic) or invokes a set of dedicated workflows: `/deepresearch` runs a planned, multi-step investigation with several parallel research passes and citation checking; `/lit` produces a literature review summarizing consensus, disagreements and open questions on a topic or research group; `/review` critiques a paper or draft with severity-graded feedback and a revision plan; `/audit` compares a paper's stated claims against its public code; `/replicate` produces a replication plan that only proceeds once the user chooses a runtime environment; `/recipe` ranks machine-learning training recipes together with datasets and reference code; `/compare` builds a source comparison matrix across a topic; and `/draft` assists with writing a paper. The project positions itself as an agent purpose-built for the research process end to end, from initial literature discovery through critical review and reproducibility checking, distinguishing it from general-purpose coding or chat agents by the specificity of its built-in research workflows. It is documented at a dedicated docs site and has a DeepWiki-generated reference, and offers a skills-only bundle for use inside other agent CLIs such as Codex and OpenCode instead of running as its own standalone process.

https://github.com/Companion-Inc/feynman

research-agentcliliterature-reviewreplicationscientific-research

Also in AI Assistants

DietrichGebert/ponytail

Ponytail enables AI agents to generate more concise, efficient, and cost-effective code by enforcing a "lazy senior dev" methodology, prioritizing existing solutions and minimal implementation.

HKUDS/DeepTutor

DeepTutor is an AI-powered personalized learning assistant that offers interactive knowledge Q&A, visualization, practice generation, and deep research capabilities to enhance education through a comprehensive and adaptive platform.

agentscope-ai/QwenPaw

QwenPaw is a personal AI assistant framework that provides local or cloud deployment, multi-channel connectivity, skill extensibility, and multi-agent collaboration for enhanced productivity and cr...

mukul975/Anthropic-Cybersecurity-Skills

A comprehensive, open-source library of 754 structured cybersecurity skills for AI agents, mapped across five prominent industry frameworks.

googleworkspace/cli

gws is a command-line tool that dynamically interfaces with Google Workspace APIs (Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin) and includes AI agent skills for automation.

nanocoai/nanoclaw

NanoClaw is a lightweight, secure AI assistant platform that runs agents in isolated containers, providing a customizable alternative to OpenClaw with native Anthropic Claude Code integration and m...

assafelovic/gpt-researcher

GPT Researcher is an autonomous AI agent that conducts deep web and local research to generate detailed, unbiased research reports with citations.

screenpipe/screenpipe

Screenpipe transforms your computer into a personal, local, and private AI that records, searches, and automates based on all your digital activities.