Bash harness to run Karpathy's autoresearch with Codex CLI in a loop. Includes A/B testing framework for comparing models.
☆57Mar 13, 2026Updated 7 months ago
Alternatives and similar repositories for codex-autoresearch-harness
Users that are interested in codex-autoresearch-harness are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- How much experts do we need to serve a model?☆154Mar 18, 2026Updated 7 months ago
- Benchmark harness for evaluating DSPy RLMs on data analysis tasks (InfiAgent-DABench)☆24Mar 22, 2026Updated 7 months ago
- Autoresearch-style AI agent loop for trading strategy optimization (SPY + VIX backtest)☆12Mar 12, 2026Updated 7 months ago
- Reference harness for the Big Finance benchmark of workflow-grounded financial-research questions☆23Oct 19, 2026Updated last week
- Karpathy's autoresearch framework adapted for autonomous prompt optimization. 74.72% → 100% accuracy in 8 experiments.☆16Mar 14, 2026Updated 7 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- The official code for paper "WeatherGFM: Learning a Weather Generalist Foundation Model via In-context Learning"☆13Mar 25, 2025Updated last year
- ☆12Sep 6, 2024Updated 2 years ago
- General plug-and-play inference library for Recursive Language Models (RLMs), supporting various sandboxes.☆17Apr 26, 2026Updated 6 months ago
- ☆16May 23, 2026Updated 5 months ago
- A Convex component for caching values that are expensive to compute☆16Updated this week
- Demo code for "The Agent Is a Workflow That Writes Itself"☆21May 14, 2026Updated 5 months ago
- 徐望瀚日常工作中使用和维护的可复用 agent skills。☆16Updated this week
- Eval Protocol (EP) is an open solution for doing reinforcement learning fine-tuning on existing agents — across any language, container, …☆42Sep 17, 2026Updated last month
- Reconstruct a meeting transcript into one self-contained HTML page: where every thread landed, with the quote that proves it.☆40Aug 21, 2026Updated 2 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 powerful and simple asynchronous task management system that divides complex tasks into subtasks, processes them concurrently using o1 …☆15Dec 26, 2024Updated last year
- Code for intro to DSPy blog post☆31Oct 13, 2025Updated last year
- ☆23Sep 7, 2026Updated last month
- 自动获取UCAS课程网站课表信息并转化为ics导出☆16Aug 31, 2025Updated last year
- Lightweight AI forward engineering standards for software development☆14Oct 11, 2026Updated 2 weeks ago
- The official repository of RadarQA☆16Jan 15, 2026Updated 9 months ago
- Curated list of awesome plugins for ChatGPT☆15Mar 23, 2023Updated 3 years ago
- This is a simple ecommers api using Golang☆13Aug 4, 2023Updated 3 years ago
- Run Qwen3.5-35B-A3B with 1 million token context on a single NVIDIA L4☆29Apr 9, 2026Updated 6 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Tiny Lab is a small Apple Silicon ML research tool with a real control plane, one shipped MLX training path, and checkpoint evaluation bu…☆95Mar 10, 2026Updated 7 months ago
- ☆12Oct 27, 2024Updated 2 years ago
- Experiments on GPT-3's ability to fit numerical models in-context.☆14Aug 11, 2022Updated 4 years ago
- A re-runnable web-search evaluation framework: in-house benchmarks + open-benchmark (SimpleQA/FreshQA) scoring with a blind pairwise judg…☆17Sep 1, 2026Updated last month
- AgentIR is a retriever specialized for Deep Research agents (COLM 2026).☆64Aug 28, 2026Updated 2 months ago
- AST-aware fast code editing via local 1.7B model☆46Jul 13, 2026Updated 3 months ago
- Fused KL divergence from hidden states for knowledge distillation☆22Apr 28, 2026Updated 6 months ago
- CLaMR: Contextualized Late-Interaction for Multimodal Content Retrieval☆27Jun 28, 2025Updated last year
- A Benchmark for Evaluating Agent Self-Evolution on Real Business Tasks☆118Updated this week
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- ☆19Jul 7, 2026Updated 3 months ago
- Convert complex business slides and scientific flowcharts into high-fidelity editable PowerPoint.☆42Aug 25, 2026Updated 2 months ago
- ☆29Jan 19, 2026Updated 9 months ago
- Your agents write each script once, well, and reuse it. Verified single-file blocks in your repo's .blocks/.☆51Oct 13, 2026Updated 2 weeks ago
- An Open Source Claude Cowork alternative built with Codex CLI☆13Jan 29, 2026Updated 9 months ago
- Obsidian plugin to sync Markdown events and tasks with Google Calendar and Google Tasks☆15Updated this week
- A clean and easy implementation of MuZero, AlphaZero and Self-Play reinforcement learning algorithms for any game.☆16Oct 15, 2024Updated 2 years ago