Documentation
Open-source framework for building retrieval, question-answering, and agentic AI applications with pipelines and components.
AI Agent Documentation & Developer Resources
Documentation, SDKs, frameworks, protocols, examples, and technical resources for building and operating agents.
Browse Documentation listings
Documentation
Official marketplace and discovery hub for OpenClaw skills, extensions, and agent capabilities.
Documentation
Lightweight Hugging Face library for building agents that reason and act through code.
Documentation
Framework for building and deploying Model Context Protocol servers for AI agents and assistants.
Documentation
Data framework for building knowledge agents and LLM applications that connect models to private and external data sources.
Documentation
Community-curated list of Hermes Agent tools, skills, tutorials, and ecosystem projects.
Documentation
Curated list focused on web agents, browser automation frameworks, and web-control infrastructure for AI agents.
Documentation
Python framework for building multi-agent workflows with handoffs, tools, tracing, and guardrails.
Documentation
Microsoft SDK for building AI agents and integrating planners, tools, memory, and model orchestration into applications.
Documentation
Google Agent Development Kit documentation and tooling for building, evaluating, and deploying AI agents.
Documentation
Curated GitHub list of AI agents, frameworks, protocols, papers, and tooling resources.
Documentation
Python agent framework from the Pydantic ecosystem for type-safe AI applications and agent workflows.
Documentation
LiveKit SDK and documentation for building production-ready voice AI agents with real-time audio, telephony, and deployment support.
Documentation
Open-source framework and ecosystem for building voice, video, and multimodal AI agents.
Documentation
Framework and platform ecosystem for building applications and agents powered by language models, tools, retrieval, and workflows.
Documentation
Git-native open standard for defining, versioning, and running AI agents.
Documentation
Documentation resource for the Agent2Agent protocol and agent interoperability concepts.
Documentation
Open standard and documentation for connecting AI agents and assistants to external tools, data sources, and services.
Documentation
Agent Network Protocol project for decentralized discovery, interaction, and hiring between AI agents.
Documentation
Open standard for packaging reusable skills that AI agents can load as structured instructions and supporting files.
Documentation
Linux Foundation open-source infrastructure project for discovery, identity, messaging, observability, and interoperability among AI agents.
About AI Agent Documentation & Developer Resources
This category maps AI agents, agentic products, and supporting tools focused on documentation workflows. Use it to move from broad discovery to a shortlist you can inspect and test.
Listings currently use directory signals such as featured status, votes, and recency to aid discovery. That order is not a quality, safety, or procurement rating, so compare the official sources before you commit.
A strong documentation listing should make its role and workflow boundary clear. Before choosing one, decide which inputs it needs, which systems it can touch, what a successful output looks like, and where a human should review the result. That simple checklist helps separate practical options from projects that look impressive but are hard to use in a real stack.
How to evaluate Documentation listings
Use this page as a shortlist, then compare each listing against the job it should perform. The right documentation option should make its value and operating boundary understandable. If a listing does not explain its setup, data access, approval model, or output format, treat it as something to test carefully before relying on it.
| Question | Why it matters | Good sign |
|---|---|---|
| What documentation task does it own? | Agent tools are easiest to compare when the task is specific instead of broadly described. | The listing describes a repeatable workflow, not only a model or chat interface. |
| Which systems can it access? | Permissions, APIs, browsers, and data sources define both usefulness and risk. | The tool explains connectors, credentials, and human approval points. |
| How are results reviewed? | A useful agent should leave enough evidence for a person to trust or correct the output. | Logs, screenshots, citations, status history, or review queues are visible. |
| Can it recover from failure? | Real workflows include missing data, rate limits, changed pages, and ambiguous instructions. | The tool exposes retries, alerts, fallbacks, or clear handoff behavior. |
Best fit
Start here when your team already knows the documentation job it wants to improve and needs a shortlist of tools to compare. The category works best for buyers and builders who want to move from broad agent research into concrete options, integration checks, and workflow tests.
Use with caution
Be careful when a listing promises broad autonomy without showing how it handles credentials, edge cases, or review. For important documentation workflows, run a small test with low-risk data before connecting sensitive accounts or letting an agent take irreversible actions.
Explore Other Categories
Frequently Asked Questions
What belongs in the documentation category?
This category groups agents, agentic products, and supporting tools whose main workflow relates to documentation. Some are complete products and others are infrastructure, so open each listing to confirm the product type and current scope.
How should I compare documentation listings?
Compare the same real task across two or three options. Record setup effort, permissions, output quality, review time, failure behavior, deployment model, and whether the result is useful without extensive rework.
Does every documentation listing run autonomously?
No. ClawSites includes autonomous agents, supervised agentic products, frameworks, infrastructure, and adjacent resources. Treat autonomy as something to verify on the official product site, not something implied by the category label.
What should I verify before using a documentation listing?
Check what data it reads, what actions it can take, where credentials are stored, what requires human approval, and what evidence remains after a run. Start with a test account or low-risk data when possible.
How are documentation listings ordered?
The directory currently uses listing signals such as featured status, votes, and recency to aid discovery. The order is not an independent quality, security, or procurement rating.
Can I submit a documentation agent or tool?
Yes. Submit a working public URL and a precise description of the job the product performs. ClawSites reviews submissions before publication and may adjust the category to keep the directory useful.
Discover more agentic projects
Browse the full AI agent directory or submit a project for review.