Skip to content

@benchflow-ai BenchFlow

All

    Repositories list

    27 repositories

    • agents

      Public
      Minimal coding agents, easy to play with (opencode TUI) and easy to benchmark (ACP on BenchFlow) — built around mini-swe-agent
      opencodeacpai-agents
      opencodeacpai-agentsterminal-uillm-evaluationcoding-agentswe-bench
      Python
      •
      Apache License 2.0
      •4•10•0•9•Updated Sep 6, 2026Sep 6, 2026

    • benchflow

      Public
      Research infra for creating RL environments, post-training, and evals.
      benchmarkevals
      benchmarkevals
      Python
      •
      Apache License 2.0
      •62•343•33•54•Updated Sep 6, 2026Sep 6, 2026

    • ClawsBench

      Public
      Repository for results and data (coming soon!) for ClawsBench
      Other
      •2•35•2•0•Updated Aug 28, 2026Aug 28, 2026

    • mini-swe-agent

      Public
      The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-b…
      Python
      •
      MIT License
      •994•1•0•0•Updated Aug 26, 2026Aug 26, 2026

    • posttrainarena

      Public
      Python
      •
      GNU Affero General Public License v3.0
      •5•14•1•3•Updated Aug 26, 2026Aug 26, 2026

    • awesome-evals

      Public
      A curated, non-BS library of the best resources for building and evaluating AI agents — papers, blogs, talks, tools, benchmarks. Maintained by BenchFlow.
      awesomebenchmarksawesome-list
      awesomebenchmarksawesome-listai-agentsrl-environmentsllmevalsllm-evaluationagent-evaluation
      Other
      •96•866•1•25•Updated Aug 20, 2026Aug 20, 2026

    • artifacts

      Public
      Python
      •
      GNU Affero General Public License v3.0
      •5•32•0•0•Updated Aug 13, 2026Aug 13, 2026

    • env0

      Public
      Python
      •
      GNU Affero General Public License v3.0
      •4•20•0•2•Updated Aug 9, 2026Aug 9, 2026

    • skillsbench

      Public
      SkillsBench evaluates how well skills work and how effective agents are at using them.
      benchmarkskillsbench
      benchmarkskillsbench
      PDDL
      •
      Apache License 2.0
      •366•1.8k•49•64•Updated Jul 23, 2026Jul 23, 2026

    • skillsbench-leaderboard

      Public
      Python
      •1•0•1•8•Updated Jul 23, 2026Jul 23, 2026

    • GenesisBench

      Public
      GenesisBench: How language intelligence can be used to improve physical intelligence.
      benchmarkroboticsagents
      benchmarkroboticsagents
      Python
      •
      GNU General Public License v3.0
      •1•4•0•0•Updated Jul 17, 2026Jul 17, 2026

    • env0-hack

      Public
      Python
      •
      GNU Affero General Public License v3.0
      •0•2•0•0•Updated Jul 1, 2026Jul 1, 2026

    • skillsbench-agentbeats

      Public
      Versioned public AgentBeats configuration for SkillsBench
      0•0•0•0•Updated Jun 21, 2026Jun 21, 2026

    • skillsbench-trajectories

      Public
      Python
      •
      GNU Affero General Public License v3.0
      •1•6•1•0•Updated Jun 14, 2026Jun 14, 2026

    • mini-swe-code

      Public archive
      mini-swe-agent + opencode TUI (mini-opencode) — BenchFlow's standalone interactive mini-swe distribution
      Python
      •
      MIT License
      •0•0•0•0•Updated Jun 12, 2026Jun 12, 2026

    • mini-swe-acp

      Public archive
      mini-swe-agent as a BenchFlow agent — ACP shim + registration
      Python
      •
      Apache License 2.0
      •0•0•0•0•Updated Jun 12, 2026Jun 12, 2026

    • skillsbench-benchmark-service

      Public
      Valkyrie benchmark service for SkillsBench
      Python
      •1•0•0•0•Updated Jun 11, 2026Jun 11, 2026

    • benchmarks

      Public
      Python
      •
      Apache License 2.0
      •1•0•0•0•Updated May 15, 2026May 15, 2026

    • agent-client-protocol

      Public
      A protocol for connecting any editor to any agent
      Rust
      •
      Apache License 2.0
      •380•0•0•0•Updated Mar 15, 2026Mar 15, 2026

    • cli

      Public
      Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. I…
      Rust
      •
      Apache License 2.0
      •1.8k•0•0•0•Updated Mar 15, 2026Mar 15, 2026

    • gepa

      Public
      Optimize prompts, code, and more with AI-powered Reflective Text Evolution
      Jupyter Notebook
      •
      MIT License
      •540•0•0•0•Updated Mar 3, 2026Mar 3, 2026

    • terminal-bench-3

      Public
      🚧 Accepting Task Submissions 🚧
      Python
      •467•0•0•0•Updated Feb 17, 2026Feb 17, 2026

    • harbor-datasets

      Public
      Python
      •126•0•0•0•Updated Feb 12, 2026Feb 12, 2026

    • pokemon-gym

      Public
      Python
      •8•97•0•0•Updated Jun 30, 2025Jun 30, 2025

    • paperbench

      Public
      Python
      •
      MIT License
      •1•6•0•0•Updated Apr 15, 2025Apr 15, 2025

    • jfkarena

      Public
      TypeScript
      •0•7•0•0•Updated Apr 1, 2025Apr 1, 2025

    • jfk-ocr-demo

      Public
      Python
      •0•0•0•0•Updated Mar 25, 2025Mar 25, 2025
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.