Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with grading, shared knowledge, and multi-agent evolution. Accepted at COLM 2026.
☆1,128Oct 19, 2026Updated 3 weeks ago
Alternatives and similar repositories for CORAL
Users that are interested in CORAL are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- AI-Driven Scientific, Algorithmic, and Systems Discovery☆758Sep 14, 2026Updated last month
- ThetaEvolve: Test-time Learning on Open Problems, enabling RL training on AlphaEvolve/OpenEvolve and emphasizing scaling test-time comput…☆184Feb 27, 2026Updated 8 months ago
- Open-source implementation of AlphaEvolve☆7,769Updated this week
- 🌊 Evaluation infrastructure for self-evolving agents, on the Harbor task standard.☆31Updated this week
- ShinkaEvolve: Towards Open-Ended and Sample-Efficient Program Evolution 🧬☆1,507Updated this week
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- A benchmark for evaluating LLMs on open-ended CS problems. Exploring the Next Frontier of Computer Science.☆347Nov 1, 2026Updated last week
- The official repository of "Position: Agentic Evolution is the Path to Evolving LLMs".☆848Nov 6, 2026Updated last week
- ☆657May 24, 2026Updated 5 months ago
- Optimize prompts, code, and more with AI-powered Reflective Optimization☆7,408Updated this week
- ALMA (Automated meta-Learning of Memory designs for Agentic systems) is a framework that meta-learns memory designs to replace human-engi…☆300Oct 12, 2026Updated last month
- A benchmark for evaluating AI agents on frontier ultra long-horizon auto research tasks.☆172Aug 30, 2026Updated 2 months ago
- Official code for Meta-Harness (2603.28052)☆1,777Nov 5, 2026Updated last week
- Infrastructure for continually self‑improving agents☆7,805Updated this week
- Meta-Harness: 76.4% on Terminal-Bench 2.0 (Claude Opus 4.6)☆1,253Mar 26, 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.
- OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis☆1,269Jun 10, 2026Updated 5 months ago
- Self-referential self-improving agents that can optimize for any computable task☆2,885Jul 31, 2026Updated 3 months ago
- AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation☆792Oct 15, 2026Updated 3 weeks ago
- Measuring how well CLI agents like Claude Code or Codex CLI can post-train base LLMs on a single H100 GPU in 10 hours☆620Updated this week
- SPADE: Self-Play in Adaptive Synthetic Executable Environments☆129Nov 5, 2026Updated last week
- Formulating Optimization Programs with Self-Improving LLM Experience Library (KDD 2026 Research Track)☆29Jun 2, 2026Updated 5 months ago
- ☆36Jul 2, 2025Updated last year
- Benchmarking Open-Ended Inference Optimization by AI Agents☆54Oct 26, 2026Updated 2 weeks ago
- MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents. Accepted at ICLR 2026; Best Paper Award at the NeurIP…☆357Oct 31, 2026Updated last week
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- OpenClaw-RL: Train any agent simply by talking☆5,744May 23, 2026Updated 5 months ago
- Evolve your language agent with Agentic Context Engineering (ACE)☆1,450Aug 24, 2026Updated 2 months ago
- [COLM-LLA 2026] The official implementation for paper "AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficien…☆24Aug 23, 2026Updated 2 months ago
- A general framework for strategically scaling evaluation-driven discovery loops, discovering state-of-the-art solutions on 21 open-ended …☆190Aug 20, 2026Updated 2 months ago
- Official AHE code — Agentic Harness Engineering: observability-driven automatic evolution of coding-agent harnesses (concurrent w/ meta-h…☆969Oct 30, 2026Updated last week
- Executable, measurable, and reproducible AI4AI toward recursive self-improvement. Home of OpenMLE and Frontis-MA1.☆898Sep 17, 2026Updated last month
- 🦞 Just talk to your agent — it learns and EVOLVES 🧬.☆3,470Jun 7, 2026Updated 5 months ago
- Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞☆14,859Aug 19, 2026Updated 2 months ago
- Framework for evaluating and improving agents☆6,973Updated this week
- 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.
- curation-bench☆10Jun 12, 2026Updated 5 months ago
- The first distributed AGI system. Thousands of autonomous AI agents collaboratively train models, share experiments via P2P gossip, and p…☆2,076Oct 17, 2026Updated 3 weeks ago
- AlgoTune is a NeurIPS 2025 benchmark made up of 154 math, physics, and computer science problems. The goal is write code that solves each…☆119Jun 24, 2026Updated 4 months ago
- ☆68Sep 30, 2026Updated last month
- The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search☆7,502Dec 19, 2025Updated 10 months ago
- CodeEvolve is an open-source evolutionary coding agent for algorithm discovery and optimization.☆157Updated this week
- turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree search with parallel…☆1,502Oct 5, 2026Updated last month
Are these results useful?