LMikeH/whileai-sdk
Scientific RL and SFT post-training for AI agents: build evals that can fail, simulate situations, judge checked against people, pass@1 with a 95% interval, train with GRPO/SFT/DPO, prove every gain on a held-out set. uv add whileai
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code
$ npx degit LMikeH/whileai-sdk/.claude ./rig-whileai-sdk # inspect, then merge into .claude/ MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit LMikeH/whileai-sdk/skills/audit-your-judge .claude/skills/audit-your-judge $ npx degit LMikeH/whileai-sdk/skills/character .claude/skills/character $ npx degit LMikeH/whileai-sdk/skills/dpo-pairs .claude/skills/dpo-pairs $ npx degit LMikeH/whileai-sdk/skills/grpo-verifier .claude/skills/grpo-verifier $ npx degit LMikeH/whileai-sdk/skills/harness-search .claude/skills/harness-search $ npx degit LMikeH/whileai-sdk/skills/manage-experiments .claude/skills/manage-experiments $ npx degit LMikeH/whileai-sdk/skills/pick-a-method .claude/skills/pick-a-method $ npx degit LMikeH/whileai-sdk/skills/sft-from-traces .claude/skills/sft-from-traces $ npx degit LMikeH/whileai-sdk/skills/strengthen-your-evals .claude/skills/strengthen-your-evals $ npx degit LMikeH/whileai-sdk/skills/tool-call-efficiency .claude/skills/tool-call-efficiency $ npx degit LMikeH/whileai-sdk/skills/watch .claude/skills/watch $ npx degit LMikeH/whileai-sdk/skills/whileai-simulations .claude/skills/whileai-simulations
$ curl -fsSL --create-dirs -o .claude/agents/docs-designer.md https://raw.githubusercontent.com/LMikeH/whileai-sdk/main/.claude/agents/docs-designer.md $ curl -fsSL --create-dirs -o .claude/agents/style-guide.md https://raw.githubusercontent.com/LMikeH/whileai-sdk/main/.claude/agents/style-guide.md $ curl -fsSL --create-dirs -o .claude/agents/user-sim.md https://raw.githubusercontent.com/LMikeH/whileai-sdk/main/.claude/agents/user-sim.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (12)
audit-your-judgecharacterdpo-pairsgrpo-verifierharness-searchmanage-experimentspick-a-methodsft-from-tracesstrengthen-your-evalstool-call-efficiencywatchwhileai-simulations
Subagents (3)
| docs-designer model: opus | Reviews the Mintlify docs (docs/) and the while.ai website for the scientific style in docs/reference/constitution.md and docs/reference/style.md with a UI/UX designer's eye - information architecture |
| style-guide model: opus | Reviews the whileai SDK's public surface for developer ergonomics against docs/reference/style.md and docs/reference/constitution.md (PyTorch / DSPy / Unsloth shape, research-backed defaults from rlhf |
| user-sim model: opus | Plays a researcher or applied-AI engineer using whileai for real - their own keys, their own compute (Modal, Prime Intellect), a scientific RL/SFT recipe with a feedback loop - by following the docs a |
Similar rigs
whilehq/whileai-sdk
Scientific RL and SFT post-training for AI agents: build evals that can fail, simulate situations, judge checked against people, pass@1 with a 95% interval, train with GRPO/SFT/DPO, prove every gain on a held-out set. uv add whileai
Skill Collector 1.0k tok · · Q0
bradautomates/claude-video
Give Claude the ability to watch any video. /watch downloads, extracts frames, transcribes, hands it all to Claude.
Minimalist 1.1k tok · · Q3
koptsev63/premiere-claude-bridge
AI assistant editor for Premiere Pro and DaVinci Resolve. Open-source MCP server for Claude Code and Codex: logs footage, transcribes, builds rough cuts, makes subtitles, checks colour and loudness.
Minimalist 242 tok · · Q0
blauwtje/exo
Claude Code plugin with four stages and hooks that refuse risky commands.
Pragmatist 1.4k tok · · Q0