Programmatic memory for long-horizon LLM agents: the harness appends everything to one log, and the agent searches it with code. 97.4% on ARC-AGI-3 (arXiv:2607.20064)
☆465Nov 2, 2026Updated this week
Alternatives and similar repositories for PRO-LONG
Users that are interested in PRO-LONG are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- An ARC-AGI solution using Agentica from Symbolica☆310Feb 12, 2026Updated 8 months ago
- ☆145Aug 12, 2026Updated 2 months ago
- ☆176Mar 26, 2026Updated 7 months ago
- ☆51Updated this week
- ARC-AGI-3 Solver using Rendered Deterministic Moore Machines☆64Jul 29, 2026Updated 3 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.
- ☆49Updated this week
- A plugin for your agentic framework that optimizes code using the GEPA algorithm (Genetic-Pareto LLM-driven search).☆100Apr 28, 2026Updated 6 months ago
- The Duck: ARC-AGI-3 inference harness -- winning solution to ARC-AGI-3 Milestone 1.☆106Jul 1, 2026Updated 4 months ago
- Permanent memory for AI agents. A 426-token prompt, a script, plug and play.☆2,367Jul 31, 2026Updated 3 months ago
- ☆15Jun 11, 2026Updated 4 months ago
- ☆317Dec 12, 2025Updated 10 months ago
- ☆88Updated this week
- Exo is an agent + harness architecture that is fully recursive, able to safely edit all aspects of itself at runtime to get better at you…☆1,585Updated this week
- Simple Python Game Engine☆30Jan 29, 2026Updated 9 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.
- Method for Long Context RLMs using verifiable Lambda Calculus☆308Apr 24, 2026Updated 6 months ago
- ☆51Oct 22, 2026Updated last week
- ☆337Aug 3, 2026Updated 3 months ago
- RLM for coding agent☆103Feb 19, 2026Updated 8 months ago
- extract all your personal data history from cursor, codex, claude-code, windsurf, and trae☆1,353Oct 7, 2026Updated 3 weeks ago
- Technical Appendices☆21Updated this week
- A self-improving RLM agent for coding workflows and long-running autonomous tasks.☆22,553Updated this week
- Frontier ARC-AGI-3 agent: 99.86% RHAE, all 183 levels solved for $654☆51Aug 11, 2026Updated 2 months ago
- Reproduction code for Lattice Deduction Transformers☆42Updated this week
- 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.
- ☆58Updated this week
- Testing baseline LLMs performance across various models☆365Updated this week
- Use the Claude Code SDK to solve Arc AGI 3☆15Jul 18, 2025Updated last year
- A compact, SDK-only agent harness: maximum performance, minimum framework code☆17Sep 4, 2026Updated 2 months ago
- Plug-and-play PyTorch transformer research framework. Swap attention, FFN, norm, positional, connection, projection, optimizer, scheduler…☆18Oct 25, 2026Updated last week
- A rust port of con-leche☆34Updated this week
- Letta Code mod packages and examples☆25Oct 6, 2026Updated 3 weeks ago
- ARC-AGI Toolkit☆87Jun 10, 2026Updated 4 months ago
- A high performance development and dispatch library for high-performance machine learning kernels.☆38Aug 15, 2026Updated 2 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- An open source agent microharness featuring persistent agency and recursive LLMs. Of bash, by bash, for bash; it's shells all the way dow…☆1,268Updated this week
- Hilbert Operator for Progressive Encoding (HOPE), and Dispersed Elastic Fine-Tuning (DEFT).☆26Oct 27, 2026Updated last week
- TELL: Test-time Experiential Lifelong Learning – a single LLM agent that learns from experience at test time, achieving 43.9% on ARC-AGI-…☆28Apr 29, 2026Updated 6 months ago
- Official code for Meta-Harness (2603.28052)☆1,743Oct 2, 2026Updated last month
- a recursive self-improving harness designed to help your agents (and future iterations of those agents) succeed on any task☆1,317Oct 28, 2026Updated last week
- The official repository of "Position: Agentic Evolution is the Path to Evolving LLMs".☆839Aug 22, 2026Updated 2 months ago
- My submission to the ARC-AGI-3 Developer Preview Agent Compitition.☆95Jan 27, 2026Updated 9 months ago