DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to build your own self-improvement loop around evaluate() with Rsi Eval

Call evaluate() from your own loop to test each new candidate and feed scores into the next one.

Who it is forA researcher developing a recursive self-improvement method who wants to keep control of candidate generation, memory, and selection.

The problemEvaluating each candidate across benchmarks means writing execution and result handling for every task, which takes time away from the method itself.

The outcomeA Python loop that generates a candidate, scores it on chosen tasks, and uses per-task feedback to produce the next candidate.

What you need first

  • Python 3.12 or newer and git
  • Docker Engine with Compose and Buildx, or Docker Desktop, for benchmark runs
  • Codex CLI on PATH and access to a model for candidate runs
  • Harbor 0.18.0 installed through the harbor extra for benchmark runs

Steps

  1. python -m pip install -e '.[harbor]'
  2. Write a Python script that imports TargetSpec, BenchmarkSelection, RunOptions, and evaluate from Rsi Eval, following the SDK example in the README.
  3. In the loop, build a TargetSpec from your candidate directory and call evaluate() with a new output_dir for each candidate.
  4. Read result.status and each trial's task_id, status, and reward, and pass them to your candidate generator.

Prompt for your agent

Using the rsi_eval SDK, write a loop that generates a candidate in <candidate-dir>, calls evaluate() with a new output directory per candidate, and collects per-task rewards. Report the reward for each candidate across iterations. Verify that each evaluation wrote its own result.json and resolved.json.

Caveat. The README notes that bundled Codex targets need concurrency=1, and each loop iteration with a model consumes quota.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page