Feynman

Feynman

Open Source(MIT)
Verified
AI-Native

The open source AI research agent that reads papers, searches the web, and writes research drafts.

Works offline
Global
Self-hostable
MCP Ready
Free Forever
+4
Last updated: Nov 3, 2026
Open Source
Visit Site10.1k
More

Quick Answer

AI

Feynman is an open-source AI research agent for automating scientific investigation. It can search literature databases, inspect Hugging Face Hub, perform web research, and parse local documents. Best for researchers and scientists automating literature reviews and ML engineers seeking ranked training recipes. Open-source.

About FeynmanAI

Feynman is an open-source AI research agent that automates scientific investigation, experiment planning, and literature reviews. It can search literature databases, inspect Hugging Face Hub, perform web research, and parse local documents. Feynman is self-hosted and supports various LLM backends via API keys.

AI-extracted from public sources. May contain errors. Methodology · Report an error
What Makes Feynman UniqueAI

Feynman offers a unique set of research workflows like /deepresearch for plan-first investigation, /lit for literature review with consensus mapping, and /autoresearch for bounded hypothesize-experiment-measure loops. It integrates directly with scientific databases like Semantic Scholar and arXiv.

Decision Intelligence

Best For

AI
Researchers and scientists automating literature reviews
ML engineers seeking ranked training recipes grounded in papers and code
Developers building custom research workflows with subagents
Teams needing to audit paper-to-code mismatches for reproducibility
Pricing Overview

Type

Open Source

Starting Price

$0/mo

Free Trial

No

Credit Card

Not Required

Free Plan

Yes

Dimension Scores

· 4.6 avg

How good it is, across universal quality axes

Ease of Use1/10
Customization5/10
Support6/10
Integration6/10
Compliance & Data Protection1/10
Performance5/10
Planning Quality8/10
AI-scored from up to 37 public sources, reviewed by a person·High confidenceHow we score

Task Scores

· 7.6 avg

What it can do, on category-specific tasks · showing 10 of 10 tasks scoring 5+

Literature Search9/10
Knowledge Synthesis9/10
Citation Management8/10
Paper Summarization8/10
Cross Reference8/10
Peer Review Support8/10
Data Extraction7/10
Methodology Guidance7/10
Hypothesis Generation6/10
Experiment Tracking6/10

Scores are AI-estimated from publicly available data — not an independent test or a verified user rating. How we rank →

Capabilities
Search
Browsing
Writing
Data Analysis
Automation
Agent
Code
Categories
Research Science
LimitationsAI
  • -Requires Git for Windows for shell commands on Windows
  • -npm install requires Node.js >=22.22.0
  • -No built-in uninstall command; requires manual file removal
  • -Telemetry is enabled by default, though opt-out is available
  • -Sends file paths in error messages if they are within projects
  • -Pro-class model IDs are rejected in model configuration
Integrations & Connections
16 connections
F
P
+12
Perplexity
Perplexity

Accurate AI that works for your team.

SS
Semantic ScholarAPI

Literature database for academic papers

OP
OpenAlexAPI

Open research data platform

AR
arXivAPI

Preprint server for scientific papers

PU
PubMedAPI

Database of biomedical literature

EP
Europe PMCAPI

Biomedical and life sciences journal literature

CR
CrossrefAPI

DOI registration agency for scholarly content

AL
alphaXivNative

Paper search, Q&A, code reading, and annotations

Auto-updated

Fit Score

Complexity

Advanced

Company Size

Solo
Small
Medium

Team Size

Individual
Small Team

Skill Level

Expert
Features
Reads papers and searches the web
Writes research drafts with inline citations
Plans experiments and audits reproducibility claims
Supports parallel researchers for deep investigations
Integrates with literature databases (Semantic Scholar, OpenAlex, arXiv, PubMed)
Inspects Hugging Face Hub for datasets and code
Parses local PDF and office documents
Configurable thinking levels for model reasoning
Technical Capabilities
SDK Available (unknown)
MCP Compatible
Multi-Agent
Human-in-Loop
Team Features
Webhook Support (unknown)
Has Demo
Function Calling (unknown)
Sandbox Mode (unknown)
Audit Logs
No Signup
Works Offline
Requires Host App
Framework
MCP Server

Deployment

Self Hosted
Authentication
OAuth
HITL mode:
Approve
Compliance, Privacy & Trust
GDPR: No info available
SOC 2: No info available
HIPAA: No info available
Trains on user data: Unknown
Human review:
Recommended
Tech Specs
MCP Servers:
Exa

The Model(s) Behind It

Model details — extracted from public vendor sources by our pipeline (AI extraction plus a source check) or admin-entered. Shown as claimed by the vendor; not independently audited by Intelloro.

Uses Models
Bring your own model — use your own API key or endpoint
Training Data Provenance
Not disclosed
Relevant to EU AI Act Art. 53 / Annex XI (GPAI)
Supported Tools
Web Search
PDF extraction
Terminal
File System
Pricing Plans
Free
Free

Looking for more Feynman alternatives?

Explore our complete list of alternatives with filters for free, cheaper, and higher-rated options.

View All Alternatives

User Reviews

No reviews yet. Be the first to review!

Who It's For
2 roles
Computer and Information Research ScientistsLife, Physical, and Social Science Technicians, All Other
Platform, Content & Languages
3 content types
1 languages
TextCodeDocumentEnglish+7 more

Output Languages

English

Content Types

Text
Code
Document

Accepts

Text
PDF
Code
URL

Produces

Text
Document
Code
Languages: English

Frequently Asked Questions

What can Feynman do?

Feynman can: Reads papers and searches the web, Writes research drafts with inline citations, Plans experiments and audits reproducibility claims, Supports parallel researchers for deep investigations. Best for: Researchers and scientists automating literature reviews.

How much does Feynman cost?

Feynman is open source and free to self-host. Cloud hosting options may have separate pricing.

Is Feynman free?

Yes, Feynman is open source and free to self-host. Managed hosting may carry separate costs.

What makes Feynman unique?

Feynman offers a unique set of research workflows like /deepresearch for plan-first investigation, /lit for literature review with consensus mapping, and /autoresearch for bounded hypothesize-experiment-measure loops. It integrates directly with scientific databases like Semantic Scholar and arXiv.

What platforms does Feynman support?

Feynman is available on CLI.

What languages does Feynman support?

Feynman supports English.

Does Feynman work offline?

Yes, Feynman supports offline use — you can run it without an active internet connection.

Who is Feynman for?

Feynman is designed for Researchers and scientists automating literature reviews; ML engineers seeking ranked training recipes grounded in papers and code; Developers building custom research workflows with subagents.

Trust Score

60/100

Good

Based on 8 data signals

Confidence: High

Reflects publicly available data, not an independent audit

Compliance & Verified38/38
VerifiedYes
Open-source licenseMIT
Human ReviewYes
Human-in-the-loopYes
HITL TypeYes
Reliability0/10

No published data

Company17/17
Company ListedYes
Team Size1-10
FundingSeed
Health—

Not yet checked

AI-Assisted Data

Some details are AI-generated estimates — verify with the vendor.

AI-generated estimate: Best For, Description, Limitations, Quick Answer, Tagline, What Makes Unique

How we source data

AI Governance & Regulatory Disclosures

Legally-sensitive fields — extracted from public vendor sources by our pipeline (AI extraction plus a source check) or admin-entered. Shown as claimed by the vendor; not independently audited by Intelloro.

EU AI Act Risk Tier
Unclassified

Switching & Migration

Migration Difficulty
Significant Effort
Data portable as:
JSONL
Support:
Documentation
GitHub
Community
Quick Stats
MemoryLong Term
PlanningAdvanced
PlatformsCLI
LaunchedMar 2026
VerifiedNov 2026
Company & Links
Company NameCompanion, Inc.
Founded2025
Based inGlobal
FundingSeed
DocumentationChangelog