Skip to content

docs: refresh README (accurate positioning + demonstration compiler prominence) #1007

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
abrichr merged 1 commit into from
Jul 13, 2026
Merged

docs: refresh README (accurate positioning + demonstration compiler prominence) #1007

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
23 changes: 19 additions & 4 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,7 @@

**OpenAdapt** is the **open** source software **adapt**er between Large Multimodal Models (LMMs) and traditional desktop and web GUIs.

Record GUI demonstrations, train ML models, and evaluate agents - all from a unified CLI.
Record a GUI workflow once, then compile it into a deterministic replay, condition a model on it, or train and evaluate agents against it — all from a unified CLI. OpenAdapt is a modular meta-package: the base install is just the CLI, and each capability (capture, compiler, ML, evals, privacy) is an optional extra you add as you need it.

[Join us on Discord](https://discord.gg/yF527cQbDG) | [Documentation](https://docs.openadapt.ai) | [OpenAdapt.ai](https://openadapt.ai)

Expand Down Expand Up @@ -93,7 +93,8 @@ openadapt capture view my-task
For workflows you run over and over, re-reasoning through every step with a
large model is slow, expensive, and non-deterministic. `openadapt-flow`
compiles a single demonstration into a script that replays **deterministically
and locally**, with no model calls on the hot path.
and locally**, with no model calls on the hot path. It ships standalone on PyPI
(`pip install openadapt-flow`, currently v0.3.x) or as an extra:

```bash
pip install openadapt[flow]
Expand All @@ -106,8 +107,22 @@ landmark geometry, then optionally a grounding model), so healthy runs cost
milliseconds. When the UI drifts, a lower rung re-resolves the target and the
fix lands back in the bundle as a reviewable diff — self-healing without a
human in the loop. When the screen stops matching expectations, the run halts
with a report instead of guessing, and identity-verified steps refuse to act on
a low-confidence match.
with a report instead of guessing, and identity-verified steps (for example a
wrong-record check) refuse to act on a low-confidence match rather than click
the wrong target.

The reference backend is a headless browser, which is why the whole loop runs
in CI with no OS permissions; desktop and RDP backends are adapters in
progress, not yet production paths. Compiled workflows can also be emitted as
Agent Skills or MCP servers so other agents can invoke them.

In one field test against a computer-use agent on a real third-party EMR
(OpenEMR's public demo), compiled replay matched the agent's success (20/20
compiled vs 10/10 agent) at roughly half the median latency and near-zero
marginal cost — the agent cost about $0.55 per run, the compiled replay makes
zero model calls. This is a small-sample result on a shared, daily-resetting
public demo, so it is not CI-reproducible; a CI-reproducible control and the
adversarial safety measurements are published alongside it.

Model-free on the hot path, deterministic, self-healing under drift, and honest
about what it can't resolve. See
Expand Down
Loading