Pieces

WORKING SLICE
Build a local developer-memory library by saving selected snippets and indexing one approved repository. Search exact text and optional local embeddings, then show the source file/revision before copying a result.

Build this scoped Pieces-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.

Prerequisites and limits
A Python virtual environment, writable input/output directories and sufficient disk for both originals and outputs. Bind the service to localhost.
Outside this release: Ambient desktop memory and autonomous code modification are outside the first release.

Data model and correctness
approved repositories, saved snippets, file hashes, source line ranges, annotations and search indexes
Invariant: Respect ignored/secret files; source references are revision-aware and no background screen capture or code edits happen without explicit enablement.
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: Build a local developer-memory library by saving selected snippets and indexing one approved repository. Search exact text and optional local embeddings, then show the source file/revision before copying a result. Record prerequisites, select representative user-owned fixtures and document the unsupported features: Ambient desktop memory and autonomous code modification are outside the first release.
2. Phase 2 — Durable model. Model approved repositories, saved snippets, file hashes, source line ranges, annotations and search indexes Add migrations or a versioned document format, explicit validation, stable IDs and a visible import-error report. Preserve this rule: Respect ignored/secret files; source references are revision-aware and no background screen capture or code edits happen without explicit enablement.
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. Move a file and relink a saved snippet through a reviewed match; a secret fixture excluded by rules never appears in search or an embedding request. Repeat the workflow after restart and with a denied permission or unavailable dependency; show recoverable failure rather than a success placeholder.

Acceptance
Move a file and relink a saved snippet through a reviewed match; a secret fixture excluded by rules never appears in search or an embedding request.
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: approved repositories, saved snippets, file hashes, source line ranges, annotations and search indexes
Project rule — preserve this invariant: Respect ignored/secret files; source references are revision-aware and no background screen capture or code edits happen without explicit enablement.
Project rule — acceptance evidence: Move a file and relink a saved snippet through a reviewed match; a secret fixture excluded by rules never appears in search or an embedding request.

# AGENTS.md — Build guide for Pieces

## Project scope
Build a local developer-memory library by saving selected snippets and indexing one approved repository. Search exact text and optional local embeddings, then show the source file/revision before copying a result.

Catalogue verdict: yes. A local snippet and repository-context library is a useful small build. Pieces combines a desktop app, a local engine and integrations for recalling work context; broad capture and dependable retrieval across those surfaces are substantially more involved.
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.
- 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.
- Scope boundary: Ambient desktop memory and autonomous code modification are outside the first release.

## 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.
- Domain model: approved repositories, saved snippets, file hashes, source line ranges, annotations and search indexes

## 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: Respect ignored/secret files; source references are revision-aware and no background screen capture or code edits happen without explicit enablement.
- 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: approved repositories, saved snippets, file hashes, source line ranges, annotations and search indexes
- Project rule — preserve this invariant: Respect ignored/secret files; source references are revision-aware and no background screen capture or code edits happen without explicit enablement.
- Project rule — acceptance evidence: Move a file and relink a saved snippet through a reviewed match; a secret fixture excluded by rules never appears in search or an embedding request.

## 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 Pieces-inspired workflow with owned or clearly labeled sample data: Build a local developer-memory library by saving selected snippets and indexing one approved repository. Search exact text and optional local embeddings, then show the source file/revision before copying a result.
- Publish a reproducible walkthrough with this observable result: Move a file and relink a saved snippet through a reviewed match; a secret fixture excluded by rules never appears in search or an embedding request.
- Explain who can operate this scoped tool, its setup and ongoing costs, and these remaining product gaps: Ambient desktop memory and autonomous code modification are outside the first release. Avoid guaranteed savings, performance scores or implied endorsement.

## Engineering roadmap
1. Phase 1 — Scope and fixtures. Implement this bounded workflow: Build a local developer-memory library by saving selected snippets and indexing one approved repository. Search exact text and optional local embeddings, then show the source file/revision before copying a result. Record prerequisites, select representative user-owned fixtures and document the unsupported features: Ambient desktop memory and autonomous code modification are outside the first release.
2. Phase 2 — Durable model. Model approved repositories, saved snippets, file hashes, source line ranges, annotations and search indexes Add migrations or a versioned document format, explicit validation, stable IDs and a visible import-error report. Preserve this rule: Respect ignored/secret files; source references are revision-aware and no background screen capture or code edits happen without explicit enablement.
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. Move a file and relink a saved snippet through a reviewed match; a secret fixture excluded by rules never appears in search or an embedding request. 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
- Cross-application long-term work memory
- Maintained editor and browser integrations
- The integrated desktop app and local background engine
- Polished source-context capture, retrieval and reuse

## Implementation prompt
WORKING SLICE
Build a local developer-memory library by saving selected snippets and indexing one approved repository. Search exact text and optional local embeddings, then show the source file/revision before copying a result.

Build this scoped Pieces-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.

Prerequisites and limits
A Python virtual environment, writable input/output directories and sufficient disk for both originals and outputs. Bind the service to localhost.
Outside this release: Ambient desktop memory and autonomous code modification are outside the first release.

Data model and correctness
approved repositories, saved snippets, file hashes, source line ranges, annotations and search indexes
Invariant: Respect ignored/secret files; source references are revision-aware and no background screen capture or code edits happen without explicit enablement.
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: Build a local developer-memory library by saving selected snippets and indexing one approved repository. Search exact text and optional local embeddings, then show the source file/revision before copying a result. Record prerequisites, select representative user-owned fixtures and document the unsupported features: Ambient desktop memory and autonomous code modification are outside the first release.
2. Phase 2 — Durable model. Model approved repositories, saved snippets, file hashes, source line ranges, annotations and search indexes Add migrations or a versioned document format, explicit validation, stable IDs and a visible import-error report. Preserve this rule: Respect ignored/secret files; source references are revision-aware and no background screen capture or code edits happen without explicit enablement.
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. Move a file and relink a saved snippet through a reviewed match; a secret fixture excluded by rules never appears in search or an embedding request. Repeat the workflow after restart and with a denied permission or unavailable dependency; show recoverable failure rather than a success placeholder.

Acceptance
Move a file and relink a saved snippet through a reviewed match; a secret fixture excluded by rules never appears in search or an embedding request.
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: approved repositories, saved snippets, file hashes, source line ranges, annotations and search indexes
Project rule — preserve this invariant: Respect ignored/secret files; source references are revision-aware and no background screen capture or code edits happen without explicit enablement.
Project rule — acceptance evidence: Move a file and relink a saved snippet through a reviewed match; a secret fixture excluded by rules never appears in search or an embedding request.

## 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.