docs: refresh README with honest research positioning#67
Merged
Conversation
Align openadapt-ml's README with the OpenAdapt house positioning and its actual, current maturity as experimental research code. - Frame the product as a governed demonstration compiler (openadapt-flow) whose healthy replay path makes zero model calls; position this repo as the upstream research and cost-optimization (Phase 2) surface. - Add an honest training status section: base VLMs cannot operate Windows without SFT; GRPO standalone backend is the default prototyping path while the verl backend is an integration stub raising NotImplementedError; SFT via TRL SFTTrainer is the most exercised path. - Update the architecture tree to match the current package layout (grpo, perception, export, baselines, segmentation, evals, providers). - Cross-link docs.openadapt.ai and the OpenAdaptAI/openadapt launcher; note private hardening corpora and recipes are kept out of this repo. - Remove em-dash-style separators throughout. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01NyCHrzA1psrKMFfroYbzaM
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Refreshes the
openadapt-mlREADME to match the OpenAdapt house positioning and this repo's actual maturity as experimental research code.What changed
openadapt-flow) whose healthy replay path makes zero model calls, and positions this repo as the upstream research + cost-optimization (Phase 2) surface, not a supported API.standalonebackend is the default single-GPU prototyping path while theverlbackend is an integration stub that raisesNotImplementedError; SFT via TRLSFTTraineris the most exercised path.grpo/,perception/,export/,baselines/,segmentation/,evals/,models/providers/).OpenAdaptAI/openadaptlauncher; notes that private hardening corpora and deployment-derived recipes are kept out of this repo.Docs-only change; no code touched.
🤖 Generated with Claude Code
https://claude.ai/code/session_01NyCHrzA1psrKMFfroYbzaM