RSI-Anything

RSIAgent is an open-source, training-free multi-agent framework for recursive self-improvement in unfamiliar digital environments. It uses a Curriculum Agent, Actor Agent, and Verifier Agent while keeping model parameters fixed. Its learning loop has two stages: broad recursive self-exploration, in which agents perform diverse projects and consolidate verified experience, followed by deep recursive self-exploration, in which the Curriculum Agent selects focused practice around gaps and fragile successes. The Actor Agent interacts with software through executable Python or Bash programs and visual observations; the Verifier Agent independently checks task requirements and resulting environments. Procedures, scripts, successful experiences, and failure lessons are stored in persistent memory, which is frozen and reused for downstream task execution. The repository provides runtimes and benchmark integrations for OSWorld-V2 and Agents' Last Exam, along with setup, smoke-test, batch execution, reporting, recovery, and validation utilities. It requires Python 3.12 and a Linux host with Docker and /dev/kvm for the documented benchmark runs, and is licensed under Apache License 2.0.

Zetta is an open-source closed-loop embodied harness for self-evolving physical intelligence. It keeps a base policy frozen while evolving code-based runtime critics and recovery skills when rollouts fail. Its evolution protocol clusters failed trajectories, uses a diagnostic stage to identify an observable causal failure mechanism, generates Critic-Recovery candidates under fixed tool schemas, and checks them through shadow replay, paired same-seed evaluation, and held-out seeds. Candidates are rejected or promoted based on these gates; the critic may propose recovery actions, a higher-level role approves them, and a bounded recovery actor executes only approved programs. The repository provides campaign management, rollout workers and environment backends for systems including LIBERO, RoboCasa, RoboTwin, and Genie Sim, along with manifests, tool catalogs, audit records, deployment helpers, and contract tests. It supports Python 3.10–3.12, while simulator assets, model weights, credentials, and host runtime files remain outside the repository.

Reasonix is an open-source AI coding agent built around a local engine and distributed as a self-contained static Go binary. It is designed for DeepSeek, with DeepSeek provided as a preset, while configuration can target OpenAI-compatible endpoints and optionally use separate executor and planner models. The agent can be used through a terminal or desktop app, in a browser, or from an editor through ACP; it provides plan mode, permissions, workspace sandboxing, per-turn checkpoints, and MCP- or extension-based plugins. Its context maintenance is designed around prefix-cache stability, including a stable startup environment summary and pruning of stale tool output before compaction.

ai-evaluation-framework is an open-source framework by Dreamers Inc. for benchmarking model-based solutions by accuracy, p95 latency, and estimated cost against user-defined ground-truth cases. Each task specifies fields and a scoring rule per field, including exact identifiers, normalized dates, numeric tolerances, containment, token overlap, and expected-missing values; cases can also provide alternate accepted renderings. It runs models from OpenAI, Anthropic, or an OpenAI-compatible gateway, compares results in a table, emits detailed JSON reports, and caches responses by model, task, and case so scoring rules can be changed without another model call. The repository uses document-field extraction as its worked example but accepts arbitrary text inputs such as OCR output, transcripts, and PDF text. A separate feedback server collects thumbs-up or thumbs-down responses with required comments, stores append-only JSONL data, and exposes statistics, exports, and candidate cases for human review; it does not train models. The repository includes tests using scripted mock models and is licensed under Apache-2.0.

Weco AI is an autoresearch agent platform for running and inspecting optimization experiments. It repeatedly proposes code changes, evaluates them against a fixed command and measurable goal, keeps changes that improve the score, and discards weaker attempts. Its dashboard presents the search as an experiment tree with scores and diffs, allowing users to branch from promising runs and steer an ongoing search toward a different idea. The workshop materials demonstrate the approach with Mini Parameter Golf and a Flappy Bird controller evaluated across multiple conditions, including hidden validation data and limits on editable code.