Pieces
Pieces is an on-device AI developer assistant and long-term memory tool. Pieces OS runs locally on the developer's machine and exposes a documented local REST API at http://localhost:1000 covering saved snippets (assets), the Pieces Copilot (QGPT) question/stream endpoints, local and cloud models, formats, applications, conversations, and workspace context. The same on-device API powers official OpenAPI-generated SDKs for Python, TypeScript, Dart, Kotlin, and C#.
APIs
Pieces Assets API
Create, read, update, delete, search, and stream saved snippets (assets) held in the local Pieces OS database. Served on-device over the localhost REST transport - no data leave...
Pieces Copilot (QGPT) API
The Pieces Copilot generative engine (QGPT). Ask questions grounded in relevant local snippets via POST /qgpt/question, score relevance, reprompt, and open a WebSocket at /qgpt/...
Pieces Conversations API
Manage Copilot conversations and their messages locally - create, list, rename, search, summarize, and delete conversations, and create/update/search the messages within them. S...
Pieces Models API
Enumerate and manage the LLMs available to Pieces OS - list models, download/load/unload local models (e.g. Llama, Mistral via on-device runtime), track download progress, and d...
Pieces Formats API
Read, update, reclassify, and analyze the underlying formats (code or text fragment representations) that back each asset. Served on-device by Pieces OS over the localhost trans...
Pieces Applications & Workspace API
Register applications, open/close application sessions, read the well-known health and version of the local Pieces OS instance, and manage user and OS-level context (device info...
Event Specifications
Pieces Copilot (QGPT) Streaming (On-Device WebSocket)
AsyncAPI 2.6 description of the Pieces Copilot **QGPT streaming** surface. Pieces runs **on-device**. Pieces OS is a local process that serves its API over the loopback interfac...
ASYNCAPI