RSIGym: A Flexible Environment for Recursive Self-Improvement
☆113Oct 12, 2026Updated this week
Alternatives and similar repositories for RSIGym
Users that are interested in RSIGym are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Native macOS virtual displays for visual agents, with a skill to set up and manage their work screens.☆129Updated this week
- Reproduction package for "Harness as a Language: A Minimalist Agent Framework With Maximal Expressivity" — ten agent arms across AppWorld…☆35Oct 10, 2026Updated last week
- EmbodiedJev: MuJoCo robot decision workbench with MiniCPM5-2B, Jev and compatible model APIs☆308Sep 22, 2026Updated 3 weeks ago
- A temporal context graph, a memory API, retrieval primitives, and a multiple-platform integration mesh — designed to be embedded into any…☆76Updated this week
- 4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes☆159Oct 8, 2026Updated last week
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Official repository for Beyond Pixels: From Video Priors to 4D Worlds.☆129Aug 16, 2026Updated 2 months ago
- ☆237Updated this week
- HarnessEval-W: Agentifying the Evaluation of Visual Worlds☆307Sep 7, 2026Updated last month
- Executable, measurable, and reproducible AI4AI toward recursive self-improvement. Home of OpenMLE and Frontis-MA1.☆830Sep 17, 2026Updated last month
- A framework for object-oriented agents. A minimalist agent framework with maximal expressivity.☆74Sep 11, 2026Updated last month
- Synthetic data generation, post-training, and E2B benchmark evaluation infrastructure.☆172Aug 25, 2026Updated last month
- ☆109Aug 30, 2026Updated last month
- Towards Physically Grounded Articulated 3D Assets: A Multi-Agent Pipeline and Benchmark☆102Updated this week
- Hierarchical, steerable subagent threads for pi☆111Updated 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.
- ☆196Updated this week
- ScienceDiscovery is an all‑in‑one agentic workbench built specifically for scientific research.☆165Updated this week
- ☆16Feb 21, 2026Updated 7 months ago
- ☆15Mar 26, 2024Updated 2 years ago
- SURE-Map: Self-Correcting Streaming Geometric Foundation Models☆162Sep 22, 2026Updated 3 weeks ago
- Support dsh runtime on Multica.☆70Aug 14, 2026Updated 2 months ago
- ☆183Oct 8, 2026Updated last week
- 把一个主题做成有配音、字幕、封面的讲解分析类视频 —— 全本地、用 HTML 写画面，稳定音画同步。 面向 AI 编程智能体的确定性 HTML → MP4 渲染流水线。☆174Updated this week
- ASPIRE: Agentic /Skills Discovery for Robotics☆436Updated this week
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- Self-hosted multi-machine file browser☆17Feb 10, 2026Updated 8 months ago
- Official implementation of Video Prediction Policy 2: Predict Better, Act Better☆255Updated this week
- An agent whose long-term memory is a git repo of markdown☆98Oct 6, 2026Updated last week
- Code as World: Agentic Discovery of Executable World Representations for Physical Reasoning☆420Aug 31, 2026Updated last month
- Mirror is Reflection's coding harness☆94Updated this week
- Docker Sandbox Kit Specification v3 - the kit descriptor grammar, the OCI artifact, the build frontend, and the conformance suites☆153Updated this week
- ☆21Jun 4, 2024Updated 2 years ago
- Raft source-available release mirror. One snapshot commit per release; pull requests are not accepted.☆611Updated this week
- Official implementation of UniWorld-View☆158Aug 12, 2026Updated 2 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.
- A very WIP tool for jev-ification☆40Oct 8, 2026Updated last week
- TypeSafe Jev as a decision layer for the Pi coding agent: a measured tool-call gate plus jev_ask for typed, calibrated answers☆165Updated this week
- SuperDex brings together a purpose-built physics engine, robotics authoring tools, and a scalable reinforcement learning interface in a u…☆741Updated this week
- ☆28Sep 27, 2026Updated 2 weeks ago
- Official implementation of FlowHMR, a generative model for physically plausible motion capture from monocular video.☆148Oct 5, 2026Updated last week
- ☆407Oct 10, 2026Updated last week
- Implemented a script that automatically adjusts Qwen3's inference and non-inference capabilities, based on an OpenAI-like API. The infere…☆22May 9, 2025Updated last year