# AGENTS.md — Build guide for Krisp

## Project scope
Start with offline voice-recording cleanup using a supported RNNoise integration, compare before/after audio and batch export. Treat a live virtual-microphone driver as a later separate platform project.

Catalogue verdict: kinda. You can build post-processing and maybe route audio through open models, but real-time low-latency virtual-device noise cancellation is not a one-sitting web app.
Use the implementation prompt below to define the deliverable. Complete each phase's acceptance checks before extending the scope.

## Working agreement
- Inspect the repository and its existing instructions before choosing paths, dependencies or commands. Keep one coherent stack and explain changes to the proposed architecture.
- Plan a vertical slice that accepts a real input and produces the useful output described below. Persist only the state the prompt calls for; respect memory-only and upstream-managed workflows. Use fixtures only when they are clearly labelled.
- After scaffolding, document the actual install, development, check and build commands in README and keep them synchronized with the package or project manifest. Do not report commands as successful unless they ran.
- Work in small steps. At handoff, list implemented flows, checks actually performed, remaining blockers, and any credentials or provider setup the owner must supply.
- Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization.

## Prerequisites
- A Python virtual environment, writable input/output directories and sufficient disk for both originals and outputs. Bind the service to localhost. Install FFmpeg and confirm codec support for the intended inputs.
- Implementation components: Python, FastAPI and server-rendered HTML with HTMX for a local interface. SQLite for manifests and job state, with an explicit worker process and immutable source files. FFmpeg/ffprobe for explicit media operations and browser previews; never interpolate user filenames into shell commands. A documented RNNoise library/binary integration with explicit sample-rate conversion; no live virtual audio driver.
- Scope boundary: Live-call integration, echo cancellation and cross-platform virtual drivers are outside this first build.

## Stack and architecture
- Python, FastAPI and server-rendered HTML with HTMX for a local interface.
- SQLite for manifests and job state, with an explicit worker process and immutable source files.
- FFmpeg/ffprobe for explicit media operations and browser previews; never interpolate user filenames into shell commands.
- A documented RNNoise library/binary integration with explicit sample-rate conversion; no live virtual audio driver.
- Domain model: audio sources, noise-suppression model versions, processing presets, measured output levels and exports

## Security and data integrity
- Bound file sizes and processing time, reject path traversal, and use argument arrays for subprocesses. Treat imported text as data and redact confidential source content from logs.
- Correctness boundary: Noise suppression can damage speech; keep the original and expose bypass, with no claim that all background sounds are removed.
- Save a job manifest with input hash, parameters and state. Write to temporary outputs, then atomically finalize only successful results; resume unfinished jobs without replacing originals.
- Export sources, manifests and outputs with checksums. Keep failed-job diagnostics and allow retry into a new output path; restore the database and file directory together.

## Agent implementation rules
- Project rule — data model: audio sources, noise-suppression model versions, processing presets, measured output levels and exports
- Project rule — preserve this invariant: Noise suppression can damage speech; keep the original and expose bypass, with no claim that all background sounds are removed.
- Project rule — acceptance evidence: A noisy speech fixture remains intelligible after review; an unsupported channel/sample-rate input is converted explicitly or rejected without silent distortion.

## Optional agent skills and references
- Optional external skill: [modern-python](https://github.com/trailofbits/skills/blob/main/plugins/modern-python/skills/modern-python/SKILL.md) — Set up Python projects with pyproject.toml, dependency management, linting, typing and automated checks. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
- Optional external skill: [sharp-edges](https://github.com/trailofbits/skills/blob/main/plugins/sharp-edges/skills/sharp-edges/SKILL.md) — Review security-sensitive APIs and configuration for dangerous defaults and easy-to-misuse interfaces. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
- Optional external skill: [web-design-guidelines](https://github.com/vercel-labs/agent-skills/blob/main/skills/web-design-guidelines/SKILL.md) — Review web interfaces for accessibility, keyboard focus, forms, navigation and interaction quality. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.

Read the linked SKILL.md and its dependencies before adding a skill. Select only the skills matching this project's runtime and task; their documentation does not supply API access, credentials or approval to perform external actions. Pin the reviewed revision where the tool supports it. Follow the chosen agent's documented project-level installation mechanism.

## Distribution ideas
These are optional planning notes. Obtain the owner's approval before publishing or contacting anyone.
- Demonstrate the actual Krisp-inspired workflow with owned or clearly labeled sample data: Start with offline voice-recording cleanup using a supported RNNoise integration, compare before/after audio and batch export. Treat a live virtual-microphone driver as a later separate platform project.
- Publish a reproducible walkthrough with this observable result: A noisy speech fixture remains intelligible after review; an unsupported channel/sample-rate input is converted explicitly or rejected without silent distortion.
- Explain who can operate this scoped tool, its setup and ongoing costs, and these remaining product gaps: Live-call integration, echo cancellation and cross-platform virtual drivers are outside this first build. Avoid guaranteed savings, performance scores or implied endorsement.

## Engineering roadmap
1. Phase 1 — Scope and fixtures. Implement this bounded workflow: Start with offline voice-recording cleanup using a supported RNNoise integration, compare before/after audio and batch export. Treat a live virtual-microphone driver as a later separate platform project. Record prerequisites, select representative user-owned fixtures and document the unsupported features: Live-call integration, echo cancellation and cross-platform virtual drivers are outside this first build.
2. Phase 2 — Durable model. Model audio sources, noise-suppression model versions, processing presets, measured output levels and exports Add migrations or a versioned document format, explicit validation, stable IDs and a visible import-error report. Preserve this rule: Noise suppression can damage speech; keep the original and expose bypass, with no claim that all background sounds are removed.
3. Phase 3 — Complete the first useful path. Implement the workflow's input, review and output interface, with clear controls and explicit empty/error states. Save a job manifest with input hash, parameters and state. Write to temporary outputs, then atomically finalize only successful results; resume unfinished jobs without replacing originals.
4. Phase 4 — Permissions and integration failure. Bound file sizes and processing time, reject path traversal, and use argument arrays for subprocesses. Treat imported text as data and redact confidential source content from logs. Request integration credentials and permissions only for the enabled feature; show a disconnected state instead of mock results.
5. Phase 5 — Portable handoff. Export sources, manifests and outputs with checksums. Keep failed-job diagnostics and allow retry into a new output path; restore the database and file directory together. Include setup, operating limits, fixture walkthrough and shutdown/restart instructions in the README.
6. Phase 6 — Acceptance scenarios. A noisy speech fixture remains intelligible after review; an unsupported channel/sample-rate input is converted explicitly or rejected without silent distortion. Repeat the workflow after restart and with a denied permission or unavailable dependency; show recoverable failure rather than a success placeholder.

## Paid-product capabilities outside this build
- low-latency virtual microphone
- polished app switching
- model quality
- meeting integrations
- admin controls

## Implementation prompt
WORKING SLICE
Start with offline voice-recording cleanup using a supported RNNoise integration, compare before/after audio and batch export. Treat a live virtual-microphone driver as a later separate platform project.

Build this scoped Krisp-inspired workflow with a documented data model and visible failure states.

Architecture
- Python, FastAPI and server-rendered HTML with HTMX for a local interface.
- SQLite for manifests and job state, with an explicit worker process and immutable source files.
- FFmpeg/ffprobe for explicit media operations and browser previews; never interpolate user filenames into shell commands.
- A documented RNNoise library/binary integration with explicit sample-rate conversion; no live virtual audio driver.

Prerequisites and limits
A Python virtual environment, writable input/output directories and sufficient disk for both originals and outputs. Bind the service to localhost. Install FFmpeg and confirm codec support for the intended inputs.
Outside this release: Live-call integration, echo cancellation and cross-platform virtual drivers are outside this first build.

Data model and correctness
audio sources, noise-suppression model versions, processing presets, measured output levels and exports
Invariant: Noise suppression can damage speech; keep the original and expose bypass, with no claim that all background sounds are removed.
Save a job manifest with input hash, parameters and state. Write to temporary outputs, then atomically finalize only successful results; resume unfinished jobs without replacing originals.

Security and privacy
Bound file sizes and processing time, reject path traversal, and use argument arrays for subprocesses. Treat imported text as data and redact confidential source content from logs.

Recovery and export
Export sources, manifests and outputs with checksums. Keep failed-job diagnostics and allow retry into a new output path; restore the database and file directory together.

Implementation order
1. Phase 1 — Scope and fixtures. Implement this bounded workflow: Start with offline voice-recording cleanup using a supported RNNoise integration, compare before/after audio and batch export. Treat a live virtual-microphone driver as a later separate platform project. Record prerequisites, select representative user-owned fixtures and document the unsupported features: Live-call integration, echo cancellation and cross-platform virtual drivers are outside this first build.
2. Phase 2 — Durable model. Model audio sources, noise-suppression model versions, processing presets, measured output levels and exports Add migrations or a versioned document format, explicit validation, stable IDs and a visible import-error report. Preserve this rule: Noise suppression can damage speech; keep the original and expose bypass, with no claim that all background sounds are removed.
3. Phase 3 — Complete the first useful path. Implement the workflow's input, review and output interface, with clear controls and explicit empty/error states. Save a job manifest with input hash, parameters and state. Write to temporary outputs, then atomically finalize only successful results; resume unfinished jobs without replacing originals.
4. Phase 4 — Permissions and integration failure. Bound file sizes and processing time, reject path traversal, and use argument arrays for subprocesses. Treat imported text as data and redact confidential source content from logs. Request integration credentials and permissions only for the enabled feature; show a disconnected state instead of mock results.
5. Phase 5 — Portable handoff. Export sources, manifests and outputs with checksums. Keep failed-job diagnostics and allow retry into a new output path; restore the database and file directory together. Include setup, operating limits, fixture walkthrough and shutdown/restart instructions in the README.
6. Phase 6 — Acceptance scenarios. A noisy speech fixture remains intelligible after review; an unsupported channel/sample-rate input is converted explicitly or rejected without silent distortion. Repeat the workflow after restart and with a denied permission or unavailable dependency; show recoverable failure rather than a success placeholder.

Acceptance
A noisy speech fixture remains intelligible after review; an unsupported channel/sample-rate input is converted explicitly or rejected without silent distortion.
Use real source data or clearly labeled fixtures. Explain unsupported input and provider failures; do not fabricate analytics, delivery receipts, accuracy claims or security guarantees.

Optional agent guidance
Optional external skill: [modern-python](https://github.com/trailofbits/skills/blob/main/plugins/modern-python/skills/modern-python/SKILL.md) — Set up Python projects with pyproject.toml, dependency management, linting, typing and automated checks. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
Optional external skill: [sharp-edges](https://github.com/trailofbits/skills/blob/main/plugins/sharp-edges/skills/sharp-edges/SKILL.md) — Review security-sensitive APIs and configuration for dangerous defaults and easy-to-misuse interfaces. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
Optional external skill: [web-design-guidelines](https://github.com/vercel-labs/agent-skills/blob/main/skills/web-design-guidelines/SKILL.md) — Review web interfaces for accessibility, keyboard focus, forms, navigation and interaction quality. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
Project rule — data model: audio sources, noise-suppression model versions, processing presets, measured output levels and exports
Project rule — preserve this invariant: Noise suppression can damage speech; keep the original and expose bypass, with no claim that all background sounds are removed.
Project rule — acceptance evidence: A noisy speech fixture remains intelligible after review; an unsupported channel/sample-rate input is converted explicitly or rejected without silent distortion.

## Completion evidence
Demonstrate the prompt's acceptance scenarios against the scoped workflow. Include setup from a clean checkout and failure recovery. Check persistence across restart and export/restore only for the state the prompt says to store; for memory-only tools, confirm that temporary content is discarded as specified. Record actual results and remaining limitations. A detailed plan alone does not establish a working replacement.