mira
taylorsatula/mira/AGENTS.md
high` selected by `ModelResolver`. In the streaming path, a `ProviderSwitchEvent` is yielded to the frontend (type=`provider_switch`) so it can clear partial output and display a persistent "generation hung
How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
taylorsatula/mira/AGENTS.md
high` selected by `ModelResolver`. In the streaming path, a `ProviderSwitchEvent` is yielded to the frontend (type=`provider_switch`) so it can clear partial output and display a persistent "generation hung
talkcody/talkcody/AGENTS.md
AGENT GATEWAY) and AI agent (FRAMEWORK) needs to be implemented in Rust. ## Technology Stack ### Frontend - Framework: React 19 - Language: TypeScript - Styling: Tailwind CSS + Shadcn UI - Testing: Vitest - State Management: Zustand
angelnicolasc/graymatter/AGENTS.md
reply. ## Identity Pick a stable `agent_id` of the form ` - ` (e.g. `graymatter-backend`, `okuna-frontend`). Don't invent a new ID per session — that defeats persistence. ## Shared facts (`__shared__`) Project
angelnicolasc/graymatter/docs/AGENTS.md
decisions/013-structured-tool-results.md)). ```jsonc // memory_search — content (text) "Found 3 relevant memories for agent \"frontend-agent\":\n\n1. User prefers TypeScript with strict mode\n2. Project uses pnpm, not npm\n3. Auth
vercel-labs/personal-agent-template/AGENTS.md
Quick start and feature overview ## Eve Framework This project uses Eve with a Nuxt frontend (`eve/nuxt` module). Before writing agent code, read the relevant guide in `node_modules/eve/docs/` — start with
jasonjgardner/blockbench-mcp-plugin/.agents/skills/zod/AGENTS.md
MEDIUM (Full Zod is ~17kb gzipped; Zod Mini is ~1.9kb - 85% smaller for frontend-critical bundles) --- ## References 1. [https://zod.dev/](https://zod.dev/) 2. [https://zod.dev/v4](https://zod.dev/v4) 3. [https://github.com/colinhacks/zod](https://github.com/colinhacks/zod)
ratel-ai/ratel/AGENTS.md
logic / library code — write the failing test first, then the implementation (red → green → refactor). Frontend code without business logic can skip. See [CONTRIBUTING.md](CONTRIBUTING.md). - **Backend before frontend**: features that aren
xpert-ai/xpert/AGENTS.md
business error keys only to the nested `en/**` or `zh/**` `nestjs-i18n` resource files. ## Frontend (Angular) - Services live in `apps/cloud/src/app/@core/services`; export them via the barrel. - New settings pages belong
mudrii/openclaw-dashboard/AGENTS.md
changes. - Use the `go-review` skill when the task is review-first. - Use the `frontend-dashboard` skill when changing the embedded SPA or dashboard UI. - Use the `project-ops` skill
Dicklesworthstone/ntm/AGENTS.md
Repos in One Product - Option A: Same `project_key` for all; use specific reservations (`frontend/**`, `backend/**`). - Option B: Different projects linked via `macro_contact_handshake` or `request_contact` / `respond_contact
platformplatform/PlatformPlatform/AGENTS.md
build`. **Slow:** Aspire restart, backend format, backend lint, end-to-end tests. **Fast:** frontend format/lint, backend test. **Aspire**: The `aspire-restart` skill manages the AppHost - always use it; never `aspire
apm-studio/apm-studio/AGENTS.md
Treat it as a separate project from this Studio repo. ## Top-Level Structure - `src/` - Frontend application. - Main UI, canvas, local Packages drawer, Import page, Export page, assistant chat, agent chat
JetBrains/kotlin-toolchain/AGENTS.md
where it is located in the project. ## Processes * When changing anything in the frontend schema, update golden test files by running: `./kotlin do updateGoldFiles` * When updating user-visible default versions
Arvo-AI/aurora/AGENTS.md
shows last 50 lines, follows) - **Rebuild API**: `make rebuild-server` (rebuild aurora-server only) - **Frontend lint**: `cd client && npm run lint` - **Frontend build**: `cd client && npm run build` - **Backend logs
vivekchand/clawmetry/AGENTS.md
default. It's a Flask app with an embedded, no-build vanilla-JS frontend; a sync daemon ingests filesystem/gateway/OTLP data into a local **DuckDB** store, and the app reads from
caipe-io/ai-platform-engineering/AGENTS.md
ingestors, graphrag, ontology skills_middleware/ # Skill scanning / catalog middleware utils/ # Shared utilities ui/ # Next.js frontend docs/ # Documentation site (Docusaurus) docker-compose*.yaml # Canonical Docker Compose configurations tests/ # Repo-level + RBAC
langchain-ai/docs/AGENTS.md
Agents | `src/oss/deepagents/` | Get started, Deployment (Going to production), Execution environment, Context management, Delegation, Steering, Frontend (Patterns), Protocols | | Managed Deep Agents | `src/langsmith/managed-deep-agents*.mdx` | Get started, Agent definition (Channels), Build and deploy
bybren-llc/safe-agentic-workflow/AGENTS.md
code | Pattern-first development (MANDATORY) | | `rls-patterns` | Database operations | RLS context helpers (withUserContext, etc.) | | `frontend-patterns` | UI work | Clerk, shadcn, Next.js patterns | | `api-patterns` | API route creation | Route structure, error
waynesutton/convexskills/AGENTS.md
functions` | writing any function in `convex/` | | `convex-schema-validator` | tables, validators, indexes | | `convex-realtime` | frontend subscriptions, optimistic updates | | `convex-http-actions` | webhooks, REST, CORS | | `convex-file-storage` | uploads, serving, metadata
waynesutton/convexskills/templates/AGENTS.md
what it does and who uses it.] Stack: Convex (backend), [React / Next.js / Vite / Expo] (frontend), [auth provider], [email provider]. ## Docs first For any Convex API, fetch https://docs.convex.dev/llms.txt
An open format for instructions to coding agents, read by Codex, Cursor and others. Think of it as a README written for agents.
At the repository root, with more specific files in subdirectories. Agents read the one closest to the file they're editing.
Setup and test commands, code style, and the rules a new contributor would need to know.
Claude Code reads CLAUDE.md. A one-line CLAUDE.md that points at AGENTS.md covers both.