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
☆127Aug 19, 2026Updated this week
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.☆36Jun 18, 2026Updated 2 months ago
- Pi extension that tracks bash tool token usage with live stats, grouping, and export☆23Feb 10, 2026Updated 6 months ago
- Work with Pi☆15Feb 9, 2026Updated 6 months ago
- AI coding assistant with code traceability☆35Jul 19, 2026Updated last month
- Conditional tool activations and approvals for the AI SDK, fully type-safe☆18Jul 8, 2026Updated last month
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Open, agent-agnostic MCP server exposing macOS computer use to any MCP client (Claude Code, Cursor, Codex, …). Background-safe, works on …☆44Updated this week
- A monorepo of extensions and skills by yours truly.☆323Updated this week
- Explore solana accounts via an interconnected graph interface☆15Jul 7, 2026Updated last month
- AI Agents designed to help manage and update EventCatalog for users☆41Jul 7, 2026Updated last month
- Agentic SDLC with local LLM's.☆17Aug 11, 2026Updated last week
- ☆14Apr 20, 2026Updated 4 months ago
- A TypeScript library that enables AI agents to leverage MCP (Model Context Protocol) servers for enhanced capabilities. This library inte…☆21Aug 11, 2025Updated last year
- Factory's Droid actions☆52Updated this week
- Official implementation of Stackelberg PPO for morphology–control co-design.☆17Mar 17, 2026Updated 5 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Line-numbered patch format. Non-sequential, llm and stream-friendly☆16Nov 7, 2024Updated last year
- PostgreSQL-backed virtual filesystem with a bash interface.☆21Aug 13, 2026Updated last week
- A simple oss SDK for spinning sandboxes with one clean syntax.☆66Jul 30, 2026Updated 3 weeks ago
- Self extensible agent harness☆22Jul 17, 2026Updated last month
- Claude Code conversation history☆24Jul 31, 2025Updated last year
- A fast, memory-efficient exact MaxSim kernel for late-interaction retrieval and reranking.☆26May 27, 2026Updated 2 months ago
- Simple meeting diarization and speaker id assistant for meetings.☆12Feb 10, 2025Updated last year
- Collect, review, and upload redacted pi session files to a Hugging Face dataset☆246Apr 13, 2026Updated 4 months ago
- Strict Red-Green-Refactor CLI gate for coding agents☆23May 28, 2026Updated 2 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ☆28Apr 25, 2026Updated 3 months ago
- Scan GitHub forks of your repo for patterns worth upstreaming. A Pi extension.☆16Apr 17, 2026Updated 4 months ago
- Awesome List / Resources for Account Abstraction☆10Dec 14, 2022Updated 3 years ago
- 💧 Query mode for agents☆105May 11, 2026Updated 3 months ago
- Frenrug on-chain AI agent smart contracts.☆14Nov 30, 2023Updated 2 years ago
- llms can learn their own context compression via RL☆49Nov 26, 2025Updated 8 months ago
- Permissionless infrastructure for agents. No human intervention required.☆45Mar 7, 2026Updated 5 months ago
- A multiplayer open-source background agent inspired by Ramp Inspect, powered by Docker, Claude Code and Vercel's agent-browser.☆24Feb 19, 2026Updated 6 months ago
- Pi Agent as add-in for M365 Office Word☆15May 6, 2026Updated 3 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.
- A /review workflow with automatic base branch detection☆15May 28, 2026Updated 2 months ago
- An opensource DevSecOps Layer for your AI agent. Governance, Custom Guard Rails and Observablity at one platform.☆20Aug 7, 2026Updated 2 weeks ago
- create silos on your mac for multiple claude instances☆67Jul 16, 2026Updated last month
- Compact, local-first neuro-symbolic assistant in Rust with a 200 MiB Bitwork cognitive model, exact reasoning tools, governed memory, and…☆43Jul 24, 2026Updated 3 weeks ago
- Evidence-backed proof for launching the Codex desktop app on Linux through an unofficial local wrapper☆40Jul 3, 2026Updated last month
- Code based orchestration for any coding agent.☆136Jun 29, 2026Updated last month
- Harbor agent adapter for pi coding agent to run Terminal-Bench evaluations☆31Dec 1, 2025Updated 8 months ago