Terminal Bench Science AI Agent

by harbor-framework• 798•• Not scanned yet•Claim this listing•Request removal
Coding Agentsagentic aiai for scienceai4science

Terminal-Bench-Science: Evaluating AI agents on research workflows across scientific domains

Terminal Bench Science is an open-source ai agent by harbor-framework, written mainly in Python, with 798 GitHub stars and the Apache-2.0 license. Its code was last updated Nov 1, 2026.

aboutREADMEsecurityreviews
Scan couldn't complete

We tried to scan this repository but the run didn't finish, often because the project needs extra setup to build. It has not been fully scanned: read the source and limit what it can access. The maintainer can claim the listing and start a new scan.

Terminal Bench Science alternatives

View more →

Similar ai agents in Coding Agents, ranked by GitHub stars. Compare licence, recent activity and scan status before you choose.

NameStarsLicenceLast updatedScan
Terminal Bench Science (this page)
harbor-framework
798Apache-2.0Nov 1, 2026Scanned, see report
AutoGPT
Significant-Gravitas
188kNone foundNov 1, 2026Not scanned yet
Langchain
langchain-ai
149kMITNov 1, 2026Scanned, no flagged issues
Gemini CLI
google-gemini
109kApache-2.0Nov 1, 2026Scanned, no flagged issues
MetaGPT
FoundationAgents
71kMITJan 21, 2026Scanned, no flagged issues
Oh My Openagent
code-yeongyu
71kNone foundNov 1, 2026Not scanned yet