ALMA (Automated meta-Learning of Memory designs for Agentic systems) is a framework that meta-learns memory designs to replace human-engineered designs for agentic system.
☆295Apr 8, 2026Updated 5 months ago
Alternatives and similar repositories for alma
Users that are interested in alma are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICLR26] AI-based scaling law discovery☆36Jan 30, 2026Updated 7 months ago
- An ARC-AGI solution using Agentica from Symbolica☆311Feb 12, 2026Updated 7 months ago
- AI-Driven Scientific, Algorithmic, and Systems Discovery☆681Updated this week
- ☆112Jun 10, 2026Updated 3 months ago
- Meta-Reinforcement Learning with Self-Reflection☆35Mar 26, 2026Updated 5 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.
- Evolve your language agent with Agentic Context Engineering (ACE)☆1,320Aug 24, 2026Updated 3 weeks ago
- Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with grading, shared knowledge, and mu…☆1,002Sep 8, 2026Updated last week
- RLM for coding agent☆102Feb 19, 2026Updated 7 months ago
- ☆637May 24, 2026Updated 3 months ago
- ☆46Feb 20, 2026Updated 6 months ago
- Official implementation of the ΔBelief-RL method.☆31Feb 28, 2026Updated 6 months ago
- [COLM-LLA 2026] The official implementation for paper "AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficien…☆24Aug 23, 2026Updated 3 weeks ago
- Implementation of SOAR☆57Sep 17, 2025Updated last year
- ☆76Jan 18, 2026Updated 8 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.
- The official repository of ALE-Bench☆220Sep 11, 2026Updated last week
- ThetaEvolve: Test-time Learning on Open Problems, enabling RL training on AlphaEvolve/OpenEvolve and emphasizing scaling test-time comput…☆179Feb 27, 2026Updated 6 months ago
- Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agents☆2,342Aug 13, 2025Updated last year
- Generate realistic multi-agent workflow traces with LLM-enriched content, semantic validation, and PM4Py compatibility. pip install open-…☆16Apr 8, 2026Updated 5 months ago
- TEVO: evolve LM motifs cheaply, then validate them in downstream train.py loops.☆19Apr 18, 2026Updated 5 months ago
- Compiles AI agent traces and truns them into reusable context.☆97Updated this week
- A benchmark for evaluating LLMs on open-ended CS problems. Exploring the Next Frontier of Computer Science.☆316Updated this week
- FrontierSmith, a new system that uses AI to synthesize open-ended coding problems at scale☆52May 30, 2026Updated 3 months ago
- Storing long contexts in tiny caches with self-study☆328Mar 23, 2026Updated 5 months ago
- 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.
- A complete cognitive architecture on S³. One Hamilton product runs memory, learning, attention, and affect☆27Jun 1, 2026Updated 3 months ago
- ☆80Apr 26, 2026Updated 4 months ago
- OpenTinker is an RL-as-a-Service infrastructure for foundation models☆679Mar 21, 2026Updated 5 months ago
- [ICML 2026] Code for V1: Unifying Generation and Self-Verification for Parallel Reasoners.☆39Mar 5, 2026Updated 6 months ago
- ☆69May 23, 2025Updated last year
- Research artifacts from Recursive's automated AI research system☆243Jun 11, 2026Updated 3 months ago
- Optimize prompts, code, and more with AI-powered Reflective Optimization☆6,631Updated this week
- ShinkaEvolve: Towards Open-Ended and Sample-Efficient Program Evolution 🧬☆1,397Aug 21, 2026Updated 3 weeks ago
- ☆20Sep 16, 2025Updated last year
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Framework for evolving code and prompts inspired by Darwinian evolution☆518Jun 1, 2026Updated 3 months ago
- [ICML2025 Oral] LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models☆125Jul 31, 2025Updated last year
- Meta-Harness: 76.4% on Terminal-Bench 2.0 (Claude Opus 4.6)☆1,215Mar 26, 2026Updated 5 months ago
- SkillOrchestra: Learning to Route Agents via Skill Transfer☆74Mar 25, 2026Updated 5 months ago
- MMLU-Pro eval results☆15Aug 21, 2025Updated last year
- General plug-and-play inference library for Recursive Language Models (RLMs), supporting various sandboxes.☆5,633Aug 26, 2026Updated 3 weeks ago
- Self-referential self-improving agents that can optimize for any computable task☆2,746Jul 31, 2026Updated last month