Same model, different wrapper: a from-scratch benchmark comparing coding-agent harnesses (codex, pi, opencode, cursor, devin) and open models on correctness, speed, and token cost
☆137Aug 27, 2026Updated last month
Alternatives and similar repositories for openbench
Users that are interested in openbench are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Pi extension that adds a run_live_terminal tool and a live tmux widget inside Pi.☆38Aug 30, 2026Updated last month
- Red-team your RAG pipeline for prompt injection, source-document leakage, and cross-document smuggling, in CI. The gap between RAG eval (…☆28Oct 15, 2026Updated last week
- Pi extension that tracks bash tool token usage with live stats, grouping, and export☆23Feb 10, 2026Updated 8 months ago
- Work with Pi☆15Feb 9, 2026Updated 8 months ago
- Keep specialist bots, their memory, and their conversations together across projects.☆31Updated this week
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- Open-source TypeScript SDK for running code in isolated sandboxes — one typed API for E2B, Daytona, Vercel Sandbox, Railway, and more☆79Oct 9, 2026Updated 2 weeks ago
- Everybody has their Claw and so do I☆33Oct 1, 2026Updated 3 weeks ago
- ☆21Aug 11, 2026Updated 2 months ago
- Conditional tool activations and approvals for the AI SDK, fully type-safe☆19Jul 8, 2026Updated 3 months ago
- Benchmark coding agents and agent harnesses on 226 deterministic file-editing tasks with byte-exact verification and a public leaderboard…☆40Updated this week
- Git-native context layer for AI coding agents. Your team's real engineering decisions — patterns, pitfalls, conventions — live as reviewe…☆26Oct 13, 2026Updated last week
- An OS-level AI layer for Windows & MacOS powered by pi.☆19Oct 10, 2026Updated last week
- Tells you if you are impacted by the supply chain attack.☆24May 13, 2026Updated 5 months ago
- Standalone patch bundle for improving Hermes prompt-cache hits on custom /codex Responses gateways☆14Apr 15, 2026Updated 6 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Uxnan (pronounced /uʃ.nan/) is a suite of tools I built to solve a very specific problem I face as a developer: managing AI-powered codin…☆36Updated this week
- ☆43Aug 13, 2026Updated 2 months ago
- Population-guided evolutionary research for pi — evolve hypotheses, run measured experiments, keep what works.☆19Jul 29, 2026Updated 2 months ago
- Let the scripts your coding agent writes call your connected MCP servers (no extra auth)☆30Aug 19, 2026Updated 2 months ago
- Collect, review, and upload redacted pi session files to a Hugging Face dataset☆258Apr 13, 2026Updated 6 months ago
- ☆13Aug 5, 2026Updated 2 months ago
- Deterministic, local-only audit reports for Claude Code AI agent sessions. Rust + SQLite. Zero network calls. MCP server for agents.☆24Aug 27, 2026Updated last month
- ☆18Sep 18, 2026Updated last month
- Part of Cognitum platform (see cognitum-one/cognitum meta-repo)☆22Sep 10, 2026Updated last month
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- The agent that grows with you☆15Oct 14, 2026Updated last week
- Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞☆11Jan 30, 2026Updated 8 months ago
- Baton coordinates coding agents. Each worker handles a focused task, and one orchestrator checks the result.☆17Sep 8, 2026Updated last month
- Sawyer Hood's BB plugins: Cascade, Compact Nav, CoW copy, Miku Companion, SlopCop, and T3 Sidebar in one repository☆20Oct 3, 2026Updated 3 weeks ago
- DSPY Experiments☆15May 2, 2024Updated 2 years ago
- The most comprehensive comparison of platforms offering cloud runtime / sandbox / VM compute for agents. By boat.dev.☆31Oct 14, 2026Updated last week
- The visual compute platform for AI and robotics — connecting agents, GPU workloads, simulation, training, and real robots through typed w…☆23Sep 13, 2026Updated last month
- ☆523Jul 23, 2026Updated 3 months ago
- Run your Claude Code and Codex agents from one Telegram chat.☆14Oct 14, 2026Updated last week
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- A monorepo of extensions and skills by yours truly.☆408Updated this week
- Your AI team. One voice away. Desktop app + open .agents protocol.☆17Aug 6, 2026Updated 2 months ago
- pi extension that mirrors pi sessions to HumanLayer (preview)☆29Oct 6, 2026Updated 2 weeks ago
- Tiny MLX-trained schedule model with a dependency-free WebGPU runtime☆16Sep 12, 2026Updated last month
- Pier Code is a terminal-native agentic coding tool that understands your codebase and helps you move faster by handling routine tasks, ex…☆17Aug 22, 2026Updated 2 months ago
- Inspire by brainqub3 claude_code_RLM, opencode version for RLM☆14Jan 22, 2026Updated 9 months ago
- CUDA Blackwell performance fork of antirez/ds4 (DeepSeek-V4-Flash): ~4x prefill, ~1.5x decode, continuous batching, weight server, DSpark☆77Sep 4, 2026Updated last month