PydanticAGENTS.mdpydantic-ai / providers
pydantic/pydantic-ai/pydantic_ai_slim/pydantic_ai/providers/AGENTS.md
Providers own API clients, authentication, base URLs, HTTP lifecycle, and provider-level model/profile inference.
AGENTS.md examples from real projects
How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
Most stars first · from page 35Worked for most · soon
PydanticAGENTS.mdPydanticAGENTS.mdpydantic-ai / realtime
pydantic/pydantic-ai/pydantic_ai_slim/pydantic_ai/realtime/AGENTS.md
Start with the architecture walkthrough in docs/api/realtime.md and the user-facing guides under docs/realtime/: a RealtimeModel.connect() opens a provider-specific RealtimeConnection (the codec, vocabulary in codec.py), and RealtimeSession (session.py) wraps it — translating codec events into the shared message/part vocabulary from pydanticai.messages, building ordinary ModelMessage history, and running the tool loop. The provider-agnostic layout mirrors the request-response side: model.py holds the RealtimeModel ABC and inferrealtimemodel, settings.py the settings vocabulary, profiles.py the RealtimeModelProfile type (per-provider tables live in pydanticai/profiles/{google,openai,grok}.py as *realtimemodelprofile helpers), and…
PydanticAGENTS.mdpydantic-ai / toolsets
pydantic/pydantic-ai/pydantic_ai_slim/pydantic_ai/toolsets/AGENTS.md
Toolsets are reusable tool collections with lifecycle, instructions, and execution boundaries.
PydanticAGENTS.mdpydantic-ai / ui
pydantic/pydantic-ai/pydantic_ai_slim/pydantic_ai/ui/AGENTS.md
Since 3971 we decided to introduce the policy of sticking to the lower (existing) version requirement. In short, this means: - version requirement bumps are disallowed - new functionality should be gated behind version checks (including imports) - older versions don't error out when they encounter new functionality, but instead skip it The inbound half of that last rule lives in agui/forward_compat.py: AG-UI's Message and InputContent are discriminated unions, so a role or type added after the installed version is…
PydanticAGENTS.mdpydantic-ai / pydantic_ai_harness
pydantic/pydantic-ai/src/pydantic_ai_harness/AGENTS.md
pydantic-ai-harness is the first-party capability library for Pydantic AI. Pydantic AI core owns the primitive runtime: agent loop semantics, normalized messages, model/provider/profile behavior, tool execution semantics, durable execution primitives, and generic capability hooks. Harness owns optional, batteries-included compositions built from those primitives: coding-agent tools, guardrails, memory, context management, repo tools, verification loops, skills, planning, sub-agents, and other reusable agent behaviors. When a change needs new core semantics, stop and propose the Pydantic AI core change instead of reimplementing core behavior…
PydanticAGENTS.mdpydantic-ai / pydantic_clai2
pydantic/pydantic-ai/src/pydantic_clai2/AGENTS.md
Read this before touching pydantic-clai2/. The repository-level AGENTS.md still applies (no em-dashes, no Any, pyright strict, keyword-only arguments, 100% branch coverage). This file adds what is specific to the terminal shell. A thin terminal around any Pydantic AI agent. It reads a prompt, runs the agent, streams the answer, and repeats. Everything beyond that is a plugin, including the default coding tools. The three layers, and who owns what: If a change needs the agent loop to behave differently, propose…
PydanticAGENTS.mdpydantic-ai / tests
pydantic/pydantic-ai/tests/AGENTS.md
The async backend defaults to asyncio. Use uv run pytest <test-path> --anyio-backend=trio --record-mode=none to run selected portable tests on Trio without duplicating the default suite. During the Trio migration, run affected concurrency tests once per backend. Keep broad Trio runs manual or periodic; do not add a second backend to every ordinary CI matrix. The selector does not imply that every test or integration already supports Trio. VCR + public-API tests are the default. We test through the public API…
PydanticAGENTS.mdpydantic-ai / benchmarks
pydantic/pydantic-ai/tests/benchmarks/AGENTS.md
No summary in the file. Open it to read it.
1jehuangAGENTS.mdjcode
1jehuang/jcode/AGENTS.md
- Use the user's Git identity - Create commits with the configured user.name and user.email. Do not override them with Jcode, Jcode agent, or a fabricated agent email. Preserve existing contributor attribution when integrating work. If no identity is configured, ask rather than inventing one. - Welcome pull requests from everyone - Review contributions on their merits, regardless of whether the author is a maintainer, an existing contributor, a first-time contributor, or an agent. Good PRs can be merged directly…
AstralAGENTS.mdty
astral-sh/ty/AGENTS.md
Parts of .github/workflows/release.yml are generated by cargo-dist from dist-workspace.toml. Before editing the release workflow, check whether the relevant section is generated. Prefer changing dist-workspace.toml or the referenced reusable workflow instead of editing generated YAML. After modifying cargo-dist configuration, regenerate the workflow with the cargo-dist version pinned in dist-workspace.toml and inspect the resulting diff to ensure the change will survive future regenerations. For reviews of this repository's GitHub automation, CI, and release process, use the GitHub repository threat model. The ruff…
teng-linAGENTS.mdnotebooklm-py
teng-lin/notebooklm-py/AGENTS.md
Status: Active Last Updated: 2026-09-07 src/notebooklm/ contains the async client (client.py) and typed exports (init.py). - Internal: _.py and _/ (_app/, _auth/, _runtime/, _sources.py, _artifacts.py). - Adapters & Wire: cli/ (Click), mcp/ (FastMCP), server/ (FastAPI), rpc/ (batchexecute RPC facade), _android/ (gRPC session & codecs). - Tests & Data: tests/unit/, tests/integration/ (VCR), tests/server/, tests/e2e/, tests/guardrails/, tests/fault_server/, tests/cassettes/ (web/, android/). Examples in examples/, tools in scripts/. Canonical contributor install (full guide: docs/installation.md):
GoogleAGENTS.mdgvisor
google/gvisor/AGENTS.md
You are an expert Systems Engineer specializing in Linux Kernel internals, the Linux ABI, and systems programming in Go. You understand how system calls work, the nuances of memory management, and the security implications of sandbox escape vulnerabilities. gVisor is a user-space kernel, written in Go, that implements a substantial portion of the Linux system surface. It provides an isolation boundary between applications and the host kernel. - Sentry: The heart of gVisor; it acts as the "kernel" running the…
GoogleAGENTS.mdgvisor / gnome-mcp
google/gvisor/images/systemd-user/gnome-mcp/AGENTS.md
You drive a GNOME desktop through the desktop__* tools. There is nothing else to work with: no shell on that machine, no filesystem access, no APIs. If you want to know something about the desktop, you have to look at it and click on it, the same way a person sitting in front of it would. Every action tool returns the screen it produced. You do not need to ask for a screenshot after acting — you already have one.…
Hugging FaceAGENTS.mdtrl
huggingface/trl/.ai/AGENTS.md
The repository is separated into main code and experimental code. Small non-invasive improvements that make experimental code more consistent with the main codebase are encouraged, but avoid large refactors. If a PR implements a method, algorithm, or training approach from a research paper, it must also add a corresponding subsection to paper_index.md. When reviewing such PRs, ensure that paper_index.md was updated. Trainers in this repository are self-contained by design. Shared logic (generation, reward computation, metric logging, weight syncing, etc.) is…
nesquenaAGENTS.mdhermes-webui
nesquena/hermes-webui/AGENTS.md
This file is the shared entry point for AI assistants working in this repository. Keep it project-specific and safe to publish. Do not put personal machine setup, private network details, credentials, tokens, or local-only workflow notes here. Use the references that match the change; there is no blanket reading list for unrelated work. Keep subsystem-specific safety and contract requirements below. - README.md for product behavior, setup, usage, and the docs index - CONTRIBUTING.md for contribution scope, PR format, and review…
nukeopAGENTS.mdnuclear
nukeop/nuclear/AGENTS.md
Guidelines for AI coding agents working on Nuclear. Nuclear is a free, open-source music player without ads or tracking. Search for any song or artist, build playlists, and start listening.…
VercelAGENTS.mdjson-render
vercel-labs/json-render/AGENTS.md
Instructions for AI coding agents working with this codebase. Always check the latest version before installing a package. Before adding or updating any dependency, verify the current latest version on npm: Or check multiple packages at once: This ensures we don't install outdated versions that may have incompatible types or missing features. When using the Vercel AI SDK (ai package) with AI Gateway, pass the model as a plain string identifier -- do not import a provider constructor: This requires…
LangChainAGENTS.mdlangchainjs
langchain-ai/langchainjs/AGENTS.md
This document provides guidance for AI coding agents working with the LangChain.js codebase. When Corridor's analyzePlan tool is available, create a plan and use the tool to analyze it before generating or modifying code. Apply the resulting security guidance before writing code. LangChain.js is a TypeScript framework for building LLM-powered applications. It provides standard interfaces for agents, models, embeddings, vector stores, and more, enabling developers to chain together interoperable components and third-party integrations. This is a monorepo managed with pnpm…
RightNow-AIAGENTS.mdopenfang
RightNow-AI/openfang/AGENTS.md
No summary in the file. Open it to read it.
NVIDIAAGENTS.mdMegatron-LM
NVIDIA/Megatron-LM/AGENTS.md
The skills/ directory contains structured guides for common tasks (running tests, building containers, managing dependencies, submitting SLURM jobs, etc.). Always read the relevant SKILL.md before starting any task it covers…
About AGENTS.md
What is AGENTS.md?
An open format for instructions to coding agents, read by Codex, Cursor and others. Think of it as a README written for agents.
Where does it go?
At the repository root, with more specific files in subdirectories. Agents read the one closest to the file they're editing.
What should it contain?
Setup and test commands, code style, and the rules a new contributor would need to know.
Does Claude Code read it?
Claude Code reads CLAUDE.md. A one-line CLAUDE.md that points at AGENTS.md covers both.