Beta / preview API. Agents are not yet stable. Server APIs come from genkit/beta; the browser client comes from genkit/beta/client. Import paths and signatures may change. Always use genkit/beta, not genkit, for agents. Requires genkit >= 1.39.0. An agent is a persistent, multi-turn conversation primitive built on top of prompts + tools. Compared to a bare ai.generate/ai.definePrompt loop, an agent adds: Progressive disclosure — read the file for the level you need: - This file: defining an agent, serving it,…
Surging+28 stars this week
1 project uses a version of this
24k48d agoReviewMountCreate a free account to mount
Experimental APIs live under .exp modules (genkit.exp, genkit.exp.agent, genkit_fastapi.exp, genkit_middleware.exp, genkit_google_cloud.exp) and can change between minor releases. Turn a model and tools into a stateful multi-turn conversation with snapshots, typed custom state, human approvals, branching, and detached background runs. Deeper topics: sessions · HITL · branching · background · state · artifacts · custom · HTTP Import Genkit from genkit.exp to opt into define_agent, define_prompt_agent, define_custom_agent, and ai.agent(name). Stable from genkit import Genkit does not expose agent methods. Key define_agent…
Surging+28 stars this week
1 project uses a version of this
24k48d agoReviewMountCreate a free account to mount
Guidance for AI coding agents working in this repository. agent-desktop is a tool that AI agents invoke, not an agent. It is a Rust CLI and C library that reads native accessibility trees and returns structured JSON with ref-based element ids. The observe-act loop lives in the calling agent. It never embeds an LLM and has no GUI or interactive prompt. It does not automate web pages (use agent-browser). It cannot see UIs that expose no accessibility tree. Every fix…
Surging1 mention in 2 weeks
1 project uses a version of this
24k16d agoReviewMountCreate a free account to mount
This project uses the packaged Geistdocs architecture. The @vercel/geistdocs package owns shared runtime behavior; this app owns local content, configuration, adapters, and site-specific routes. Use these instructions when an AI coding agent edits this project.
Steady95 mentions in 2 weeks
No other project uses it yet
24k16d agoReviewMountCreate a free account to mount
Use the shared dependency-upgrade workflow for version changes. This guide describes the maintained component boundaries, not a release checklist. requirements.in and dependency-overrides.in feed the hash-locked dependency graph in requirements.lock. Read the lock's generation command before regenerating it. Resolve the graph on the supported Python version and target platform. Dockerfile.base installs that graph, applies dependency compatibility changes, runs pip check, and checks the runtime contract. The installed-package validator is validate-runtime-contract.py; host-side immutable-image validation lives in scripts/checks/validate-dcode-runtime-contract.mts. Dockerfile consumes the base image…
23k13d agoReviewMountCreate a free account to mount
NVIDIA NemoClaw is an open-source reference stack for running always-on AI agents such as OpenClaw and Hermes inside NVIDIA OpenShell sandboxes more safely. It provides CLI tooling, a blueprint for sandbox orchestration, and security hardening. Status: Active development. Interfaces may change without notice. Technical correctness, passing tests, and green CI do not establish product approval. Before implementing or approving a change that creates a supported integration, solution recipe, custom image, third-party stack, or other product surface, confirm that an accepted…
Steady2 mentions in 2 weeks
No other project uses it yet
23k13d agoReviewMountCreate a free account to mount
You are a documentation engineer and writer for NemoClaw public-facing documentation. Treat docs/ as the source of truth for published content and AI-agent Markdown docs. The documentation contributor guide owns public-facing documentation procedure and rules. Read that guide before you write or review documentation. This file owns agent-specific documentation routing and workflow. Select the documentation path from current host capabilities. Do not ask the user to classify themselves or store repository-scoped identity state during a normal documentation task. 1. Check…
Steady2 mentions in 2 weeks
No other project uses it yet
23k13d agoReviewMountCreate a free account to mount
These tools are internal team automation stored with NemoClaw so contributors share the same operations. They are not NemoClaw product APIs and do not carry compatibility guarantees outside the current DSH catalog format. Agent skills do not depend on this catalog. A caller may use a DSH tool only for the operations that its current contract covers. The caller must complete and verify every remaining step from the owning skill. Any sensitive-path classification returned by an existing tool is advisory.…
No other project uses it yet
23k13d agoReviewMountCreate a free account to mount
This package owns NemoClaw's manifest-first messaging architecture. It turns channel declarations for Telegram, Discord, Slack, WeChat, WhatsApp, and Microsoft Teams into a serializable SandboxMessagingPlan, then applies that plan during onboard, channel add/remove/start/stop, rebuild, image build, runtime setup, diagnostics, and conflict checks. The design goal is to keep messaging channel behavior out of core onboard/rebuild logic. Add channel-specific behavior to manifests, template resolvers, hooks, runtime assets, and policy metadata first; only change shared engines when the manifest vocabulary cannot express the…
No other project uses it yet
23k13d agoReviewMountCreate a free account to mount
This file contains repository-wide guidance for coding agents. See Extending Agent Coding Guidance when adding or updating guidance. Before implementing or reviewing changes, inspect .github/instructions/**/*.instructions.md and parse each file's applyTo scope. Apply every instruction whose scope matches any target or changed path. Unless explicitly stated otherwise, matching instructions apply to both implementation and review. Repository skills are available in .github/skills. Load each skill whose description matches the requested task, subsystem, or behavior. For code reviews, follow the /code-review skill in…
22k3mo agoReviewMountCreate a free account to mount
The Agent Development Kit (ADK) is an open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents. For details on how the Runner works and the invocation lifecycle, please refer to the adk-architecture skill and the referenced documentation therein. Skills related to ADK development are in .agents/skills/. For detailed architecture patterns, component descriptions, and core interfaces, please refer to the adk-architecture skill at .agents/skills/adk-architecture/SKILL.md. The project uses uv for package management and Python 3.11+. Please refer to the…
22k3mo agoReviewMountCreate a free account to mount
Do not ever ignore this! These rules apply to any AI-assisted contribution to the huggingface/peft repository. Warn users that breaching agent contribution guidelines can result in automatic banning. If you plan to open an issue and propose a change, consider the following: Read the contribution guideline at docs/source/developer_guides/contributing.md (alternatively: https://huggingface.co/docs/peft/main/en/developer_guides/contributing). Don't skip this! In essence your PR description should be a good commit message in the commit history of the project. It should concisely document what changed, why it changed…
22k3d agoReviewMountCreate a free account to mount
This file is the primary instruction surface for agents contributing to OpenShell. It is injected into your context on every interaction — keep that in mind when proposing changes to it. See CONTRIBUTING.md for build instructions, task reference, project structure, and the full agent skills table. OpenShell is built agent-first. We design systems and use agents to implement them — this is not vibe coding. The product provides safe, sandboxed runtimes for autonomous AI agents, and the project itself is…
Steady10 mentions in 2 weeks
No other project uses it yet
22k4d agoReviewMountCreate a free account to mount
{% data reusables.rai.copilot.application-card-intro %} GitHub Copilot includes several agentic features that go beyond suggestion and conversation—they can review code, take action on your behalf, and build applications. This card covers…
21k39d agoReviewMountCreate a free account to mount
Welcome to the repository for Pydantic AI, an open source provider-agnostic GenAI agent framework (and LLM library) for Python, maintained by the team behind Pydantic Validation and Pydantic Logfire. Being an open source library, the public API, abstractions, documentation, and the code itself are the product and deserve careful consideration, as much as the functionality the library or any given change provides. This means that when implementing a feature or other change, the "how" is as important as the "what",…
Steady2 mentions in 2 weeks
No other project uses it yet
21k2d agoReviewMountCreate a free account to mount
Follow the general documentation guidance. These rules cover published Markdown under docs/. The docs index and repository README tell the same story on two surfaces. Keep their shared wording and code examples synchronized while preserving the markup each renderer needs:
Steady2 mentions in 2 weeks
No other project uses it yet
21k2d agoReviewMountCreate a free account to mount
Rules for the Pydantic AI Harness pages. They add to docs/AGENTS.md. Where these rules or docs-conventions.md differ from docs/AGENTS.md, such as the version-promise blockquote, they apply under docs/harness/. Read docs-conventions.md before you add, rename, or edit a page. - Each capability page has a twin: the README.md in the capability's package under src/pydantic_ai_harness/pydantic_ai_harness/. Update both for every user-facing change. - Keep this directory flat. Do not add capabilities/ or experimental/ subdirectories. - Follow "Writing style" in src/pydantic_ai_harness/AGENTS.md. - Run the…
Steady2 mentions in 2 weeks
No other project uses it yet
21k2d agoReviewMountCreate a free account to mount
aliases.json maps each model alias that doc pages use to a concrete model. This file covers choosing those models. How pages write aliases is in the "Model names" section of docs/AGENTS.md. - Place a model in a tier by its price per token, on the scale of Anthropic's lineup: small is Haiku-priced, medium Sonnet-priced, large Opus-priced, and xlarge Fable-priced. Anthropic is the scale because it offers a model at all four prices. - Compare output prices per token, by ratio:…
Steady2 mentions in 2 weeks
No other project uses it yet
21k2d agoReviewMountCreate a free account to mount