Coder Agents is a chat interface and API for delegating development work and research to coding agents in your Coder deployment. Developers describe the work they want done, and Coder Agents handles selecting a template, provisioning a workspace, and executing the task.
Administrators configure LLM providers from Admin settings > AI and Coder Agents models from Admin settings > AI > Models. Providers and centrally managed credentials are deployment-wide settings managed by platform teams. Each model belongs to an organization. Each organization has its own model list. Developers…
The Tasks API (/api/v2/tasks) and the Chats API (/api/v2/chats) serve similar goals (programmatic access to AI-powered coding agents) but they differ significantly in architecture, capabilities, and usage patterns.
🌌 PARA Workspace is an open-source workspace framework that defines how humans and AI agents organize knowledge and collaborate on projects. It ships as a repo containing a kernel (constitution), CLI tools, and templates — which generates workspaces where you actually work.
🌌 PARA Workspace is an open-source workspace framework that defines how humans and AI agents organize knowledge and collaborate on projects. It ships as a repo containing a kernel (constitution), CLI tools, and templates — which generates workspaces where you actually work.
Stage 7 of the Electrobun SDLC pipeline. Fixes bugs, corrects blast radius drift (files missed or forgotten), cleans up debug artifacts, and brings the implementation into full alignment with the Architecture Spec and QA Report. Works BLOCKER → IMPORTANT → MINOR. Does not add features.
Electrobun backend specialist. Implements the bun-side of Electrobun desktop app features — BrowserWindow creation, BrowserView.defineRPC() wiring, request and message handlers, electrobun.config.ts updates, and app lifecycle. Receives an RPC contract handoff from the UI agent and produces complete, ready-to-run…
Stage 6 of the Electrobun SDLC pipeline. Writes tests that expect the golden outcome — ideal, correct behavior — not tests calibrated to what the current code does. Uses the Kitchen Sink defineTest() framework. Produces a test suite that defines the contract the feature must always honor.
A project-scanning helper that reads an existing project and creates a summary of it plus a list of conflicting information found in different sources.
A supporting agent for the cadence workflow that compares an earlier handoff snapshot with the project's current notes and reports what changed. A handoff is a written record that helps work continue in a later session.
Use this agent when the user asks to "document compliance", "write security documentation", "create audit documentation", "document GDPR", "document SOC2", "document HIPAA", "write regulatory documentation", or needs documentation for compliance requirements, security controls, audit trails, or regulatory adherence.
Analyze API endpoints, REST/GraphQL design, and client-server communication for over-fetching, missing pagination, or inefficient endpoint design. Use when user asks about API performance or runs /n1-optimizer:analyze.