Best agents

46,301 agents are in the catalogue. These 100 are the ones that pass every gate. Every gate: original work, not a copy · security scan A or B · a licence that permits reading the source · an actively maintained repository people actually use. Order is the composite score — reputation, freshness, safety, originality, content and traction — not anyone's opinion.

#ModTypeCategoryStarsScanTokensRating
1 AVM Owner Triagegithub/awesome-copilotTriage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval. Agent Project management 39k A 61
2 code-revieweranthropics/claude-cookbooksPerforms thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts. Agent Code review 52k A 52
3 AGENTSblock/buzzScope: desktop/src/features/agents/ (config surfaces, shared config renderer, and the agent config core). Read this before changing how harness / provider / model / effort configuration is modeled, rendered, persisted, or applied. Agent Other 32k A 0
4 raise-pull-requesthome-assistant/coreUse this agent when creating a pull request for the Home Assistant core repository after completing implementation work. This agent automates the PR creation process including running tests, formatting checks, and proper checkbox handling. Agent Code review 90k A 44
5 investigate-errorreact/reactInvestigates React compiler errors to determine the root cause and identify potential mitigation(s). Use this agent when the user asks to 'investigate a bug', 'debug why this fixture errors', 'understand why the compiler is failing', 'find the root cause of a compiler issue', or when they provide a snippet of code and… Agent Debugging 249k A 90
6 code-reviewerrtk-ai/rtkUse this agent when you need comprehensive code quality assurance, security vulnerability detection, or performance optimization analysis. This agent should be invoked PROACTIVELY after completing logical chunks of code implementation, before committing changes, or when preparing pull requests. Examples:\n\n… Agent Code review 79k A 0
7 go-sdk-tool-migratorgithub/github-mcp-serverAgent specializing in migrating MCP tools from mark3labs/mcp-go to modelcontextprotocol/go-sdk. Agent Languages 33k A 26
8 toolsrun-llama/llama_indexHaving proper tool abstractions is at the core of building agentic systems in LlamaIndex. Defining a set of Tools is similar to defining any API interface, with the exception that these Tools are meant for agent rather than human use. We allow users to define both a Tool as well as a ToolSpec containing a series of… Agent Building agents 52k A 0
9 claude-codemusistudio/claude-code-routerClaude Code is Anthropic's coding agent. CCR supports both of its surfaces. Agent Building agents 37k A 0
10 connect-clients-syncComposioHQ/composioSyncs AI client definitions from the dashboard repo (ComposioHQ/composiodashboard) to the Composio Connect docs page. Agent Web3 and blockchain 30k A 0
11 agent_typesmicrosoft/UFOThis document describes how the unified three-layer Device Agent architecture is implemented across different platforms. While the core framework (State, Processor, Command layers) remains consistent, each platform implements specialized agents optimized for their native control mechanisms and hierarchies.… Agent Hardware and IoT 9.7k A 0
12 chat-agentscloudflare/agentsBuild AI-powered chat interfaces with AIChatAgent and useAgentChat. Messages are automatically persisted to SQLite, streams resume on disconnect, and tool calls work across server and client. Agent Frontend 5.5k A 0
13 new_model_supportaxolotl-ai-cloud/axolotlGuide for debugging and adding support for new model architectures in axolotl. Based on lessons learned from Gemma4, Gemma3, Qwen2-VL, and other multimodal/MoE models. Agent Data and AI 12k A 0
14 custom-engine-implementationgithub/gh-awComprehensive guide for implementing custom agentic engines in gh-aw. Agent Building agents 5.1k A 12
15 pm-agent-guideSuperClaude-Org/SuperClaude_FrameworkDetailed philosophy, examples, and quality standards for the PM Agent. Agent Project management 24k A 0
16 riscv-review-agentFastLED/FastLEDExpert RISC-V assembly code reviewer with deep ISA knowledge. Agent Code review 7.5k A 17
17 ROCKETRIDE_COMMON_MISTAKESrocketride-org/rocketride-serverA comprehensive guide to avoiding common pitfalls when building RocketRide pipelines and applications. Agent Writing and docs 8.0k A 0
18 basic-agentsJetBrains/koogA basic agent uses a predefined strategy with a simple execution flow that works for most common use cases. It accepts a string input (a question, request, or task description) and sends this input to the configured LLM. The LLM may decide to call provided tools. The agent will execute the tools and send the results… Agent Building agents 4.6k A 0
19 beeaiIBM/mcp-context-forgeBeeAI Framework is a dual-language framework for building agentic applications in Python and TypeScript. It can use tools exposed by any MCP server through BeeAI's MCPTool, which discovers remote tools from an MCP client and makes them available to BeeAI agents. Agent DevOps and cloud 4.4k A 0
20 contextVoltAgent/voltagentPass custom data through agent operations using context. Agent Building agents 11k A 9
21 build-agent-empty-input-diagnosisalvinunreal/oh-my-opencode-slimStatus: Resolved for interview injections. Date: 2026-08-10 Related PR: #818 (fix/preset-tui-slash-command) — same root class as the original /preset fix. Suspected sibling bug reported by user: During superpowers / brainstorm skill conversations, when the orchestrator asks for confirmation or work is interrupted… Agent Debugging 8.7k A 0
22 docs-parity-reviewerpydantic/montyUse as the documentation gate before a branch or PR merges. Verifies that a user-visible change is reflected across all four documentation surfaces (README.md, docs/, limitations/, crate READMEs), that no divergence leaked into docs/ instead of limitations/, and that every snippet runs. Reports findings; does not edit. Agent Code review 8.2k A 69
23 project-manager-backlogMrLesk/Backlog.mdUse this agent when you need to manage project tasks using the backlog.md CLI tool. This includes creating new tasks, editing tasks, ensuring tasks follow the proper format and guidelines, breaking down large tasks into atomic units, and maintaining the project's task management workflow. Examples: Context: User wants… Agent Project management 6.6k A 0
24 contextlangchain-ai/langgraphjsAgents often require more than a list of messages to function effectively. They need context. Agent Writing and docs 3.3k A 0
25 mcpc-testerapify/apify-mcp-serverProbe the local Apify MCP server with mcpc during development. Use proactively after implementing features or fixing bugs to test that the implementation follows the spec, confirm requirements are met, and discover failing or missing behavior. Agent Testing 6.1k A 47
26 amplifier-expertmicrosoft/amplifierYou are the authoritative consultant for the complete Amplifier ecosystem. Other agents should consult you for. Agent Research 3.1k A 0
27 component-example-creatorchakra-ui/arkUse this agent when the user requests examples for a component, asks to add stories to a component, needs documentation examples updated, or mentions creating/updating component demonstrations. Examples:\n\n \nContext: User is working on the Checkbox component and wants to add new usage examples.\nuser: "Can you… Agent Frontend 5.4k A 0
28 planning-agents-guidedarrenhinde/OpenAgentsControlThe planning agent ecosystem consists of five specialized agents that work together to transform feature requirements into actionable implementation plans. Agent Planning 4.8k A 0
29 Backend Developermicrosoft/skillsFastAPI/Python specialist for CoreAI DIY backend development with Pydantic, Cosmos DB, and Azure services. Agent Languages 3.0k A 25
30 reviewercompanion-inc/feynmanRun tough but constructive internal research critique of an AI research artifact. Agent Research 8.9k A 16
31 s3-providerskenn-io/agentsviewRead this file before enabling S3 ingest for an agent, changing S3Provider / Source.S3Discovery, or altering S3 discovery, session IDs, temp materialization, or post-fetch hydrate. Agent DevOps and cloud 5.8k A 0
32 rust-reviewerfallow-rs/fallowReviews Rust code changes for correctness, performance, and project conventions. Agent Languages 4.4k A 16
33 semble-searchMinishLab/sembleCode search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over runshellcommand/readfile for any semantic or exploratory question. Agent Debugging 6.0k A 46
34 reviewerentireio/cliCode review agent - critically reviews changes for quality, security, and correctness. Agent Code review 5.1k A 17
35 pull-requestscallstack/agent-deviceAgent "pull-requests" from callstack/agent-device, covering pull requests, readiness, validation lifecycle, commits and rebasing onto a moving main. Agent Mobile 4.4k A 0
36 piopenagents-org/openagentsOpenAgents supports Pi, Earendil's coding agent for the terminal — executable pi, distributed as the npm package @earendil-works/pi-coding-agent. Agent Building agents 4.0k A 0
37 environmentsevalstate/fast-agentRun shell and filesystem tools in local, Docker, Hugging Face, or custom environments. Agent Other 3.9k A 18
38 auth-and-securitykiali/kialiKiali's authentication system lives in handlers/authentication/. At startup a single AuthController is instantiated based on the auth.strategy configuration field. The controller drives the full session lifecycle: login, per-request validation, and logout. Agent Security 3.6k A 0
39 instructions-writerVRSEN/agency-swarmWrite optimized agent instructions using prompt engineering best practices. Agent Building agents 4.6k A 13
40 custom-agentsgoogle/adk-docsSupported in ADK Python v0.1.0 TypeScript v0.2.0 Go v0.1.0 Java v0.1.0 Kotlin v0.1.0. Agent Building agents 1.5k A 0
41 FStarDevFStarLang/FStarAn F compiler developer agent for build, bootstrap, and compiler engineering tasks. Agent Languages 3.1k A 19
42 notebook-writerdgunning/edgartoolsUse this agent to create SEO-targeted Google Colab notebooks for edgartools. Each notebook targets a specific search query (e.g., "download 10-K filings python free"), follows the Colab cell template (badge, install, wow moment, progressive disclosure), and positions edgartools against paid alternatives. Use this… Agent Documents 2.7k A 0
43 Squadmicrosoft/wazaYour AI team. Describe what you're building, get a team of specialists that live in your repo. Agent Project management 1.3k A 23
44 beads-wardenjeremylongshore/tons-of-skills-marketplaceGuard the beads execution record: enforce the write-flush-verify discipline that defeats the bd rapid-write race, audit epic dependency graphs for cycles and orphans, catch closures whose title overstates what shipped, flag open beads carrying no disposition or a disproven premise, and reconcile bd against its GitHub… Agent DevOps and cloud 2.7k A 157
45 qa-checklistlevy-street/world-of-claudecraftEvergreen end-of-contribution QA gate for World of ClaudeCraft. Use PROACTIVELY whenever a change is complete and before it is called done. Reads the diff, cross-references the root and sub-directory CLAUDE.md rules, runs the matching guard tests, and checks every repo invariant in play: determinism and sim purity… Agent Game development 2.2k A 164
46 editorTheCraigHewitt/seomachineYou are a professional content editor specializing in making technical content sound human, engaging, and authentic while maintaining accuracy and SEO value. Agent Writing and docs 7.4k A 0
47 CLAUDEPrefectHQ/marvinAI agents with tool access, memory, and autonomous decision-making capabilities. Agent Building agents 6.2k A 0
48 tdd-developmentsamanhappy/mcphubTDD Development Agent - Diagnose bugs and implement features using a test-driven development workflow. Agent Debugging 2.4k A 16
49 seam-analyzerWirasm/prpHunts for a missing type at a seam — structure flattened and rebuilt downstream, hand-maintained lists held together by KEEP IN SYNC comments, a phase that exists in the code but not in the type, a second route that skips the validator, an invariant carried by a comment or by a helper with a reachable bypass, a type… Agent Code review 2.2k A 177
50 triagerAzure-Samples/azure-search-openai-demoTriage old stale issues for obsolescence and recommend closures. Agent Project management 7.8k A 12
51 database-reviewerzereight/gitlab-mcpDatabase code review specialist with embedded style and safety rules. Use when: reviewing SQL queries, ORM code, database migrations, query performance, database-specific patterns, schema design, transaction management. Agent Databases 2.0k A 41
52 AGENT_RUNTIMETeam-Commonly/commonlyCommonly is a platform-only core. Agents run externally and connect to Commonly using runtime tokens. Agent Building agents 1.3k A 0
53 Code Review (Codex)microsoft/agentrcCode review following VS Code contribution standards — correctness, lifecycle, naming, layering, accessibility, and security. Agent Code review 1.0k A 26
54 agentServerConversationsmicrosoft/TypeAgentThe agentServer manages explicit, named conversations with full CRUD semantics. Each conversation has its own isolated dispatcher instance, chat history, conversation memory, and persist directory. Multiple clients can connect to the same conversation simultaneously and share state; clients connected to different… Agent Building agents 739 A 0
55 Documentation Update Agentmicrosoft/wassetteSpecialized agent for creating, updating, and maintaining Wassette project documentation using mdBook. Agent Writing and docs 941 A 21
56 multi-server-state-isolationuzairansaruzi/hermexWhich app state is per-server versus intentionally global, where each lives, and which tests guard the isolation. Almost all isolation holds by construction through the server-keyed view tree and cache keys described below; "Clear Offline Cache" is explicitly scoped to the active server. Agent Debugging 1.2k A 0
57 web-search-agentWeizhena/Deep-Research-skillsUse this agent when you need to research information on the internet, particularly for debugging issues, finding solutions to technical problems, or gathering comprehensive information from multiple sources. This agent excels at finding relevant discussions. Use when you need creative search strategies, thorough… Agent Research 2.1k A 66
58 callbacksmozilla-ai/any-agentCallbacks provide hooks into the lifecycle of an AnyAgent execution. Using callbacks, you can monitor, control, and extend agent behavior without modifying the core underlying agent logic. Agent Building agents 1.2k A 0
59 agentic-workflowsAzure/azure-devGitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing. Agent DevOps and cloud 568 A 24
60 code-simplifierAlex-Rachel/TEngineUse this agent when the user wants to simplify, refactor, or optimize existing code for better readability, maintainability, and performance. This includes removing redundant logic, adding Chinese method comments, improving code structure, and ensuring coding standards compliance. Examples:\n\n- User… Agent Code review 2.3k A 281
61 instructionsactiveagents/activeagentSystem-level messages that guide agent behavior, personality, capabilities, and tool usage. The agent's operating manual for every interaction. Agent Building agents 971 A 25
62 package-docs-generatorformkit/formkitUse this agent when the user wants to generate, update, or create CLAUDE.md documentation for a FormKit package. This includes when the user asks to document a specific package's architecture, wants to understand how a package works, or needs to create onboarding documentation for future LLMs working with the… Agent Writing and docs 4.8k A 0
63 adding-an-agent-providermattpocock/sandcastleThis document is for contributors adding support for a new agent (e.g. Claude Code, Codex, gemini-cli) as a built-in agent provider. It covers. Agent Building agents 7.9k A 0
64 library_book_renewal.sopstrands-agents/samplesThis SOP guides the Library Book Renewal Agent through processing user requests to renew library books while ensuring compliance with library policies, proper workflow execution, and positive user communication. Agent Productivity 840 A 0
65 acceptance-test-generatorshinpr/claude-code-workflowsGenerates integration/E2E test skeletons from Design Doc ACs using ROI-based selection and journey-based E2E reservation. Use when Design Doc is complete and test design is needed, or when "test skeleton/AC/acceptance criteria" is mentioned. Behavior-first approach for minimal tests with maximum coverage. Agent Productivity 679 A 68
66 design-system-checkerJimLiu/baoyu-designYou are a read-only validator for a portable design system. Your only job is to run the checker script, relay what it found, and add a one-line health summary. You must not modify, create, or delete any file, run the compiler, serve anything, or take any other action. You read and report — nothing else. Agent Design and UX 3.9k A 0
67 hardnessanymouschina/TapCanvasAgent "hardness" from anymouschina/TapCanvas, covering harness design for long-running application development, why naive implementations fall short, frontend design: making subjective quality gradable, scaling to full-stack coding and the architecture. Agent Planning 593 A 0
68 genblaze-maintainerbackblaze-labs/genblazeThe Genblaze Maintainer — autonomous guardian of the Genblaze repo. Resolves GitHub issues end-to-end (branch → TDD fix → verify → merge-ready PR) and audits functional integrity, security, code quality, documentation, AI agent standards, and dependency health. Invoke with an issue number to fix it, with no prompt to… Agent Code review 558 A 100
69 speckit.git.featuresnowdreamtech/frpCreate a feature branch with sequential or timestamp numbering. Agent Git and workflow 908 A 9
70 hyperresearch-instruction-criticjordan-gibbs/hyperresearchUse this agent in Layer 5 of the hyperresearch deep research pipeline. Reads the Layer 4 draft and checks it against the prompt-decomposition artifact (research/runs/ /prompt-decomposition.json) produced in Layer 0. Emits findings when atomic items from the prompt are missing, under-covered, out-of-order, or delivered… Agent Research 1.9k A 118
71 debuggerDoorman11991/smallcodeSystematic root-cause diagnosis — reproduce, hypothesize, test, fix, verify. Agent Debugging 2.0k A 21
72 building-agentspromptise-com/FoundryCreate intelligent agents that connect to MCP servers, discover tools automatically, and execute tasks with full observability. Agent Building agents 869 A 0
73 Update Copilot CompletionAlgorithmsmallmain/vscode-unify-chat-providerSynchronize this repository's Copilot completion behavior with a pinned microsoft/vscode commit while preserving reviewed completion effects and provenance. Agent Building agents 708 A 30
74 2026-06-16-flue-framework-openagents-auditOpenAgentsInc/openagentsDate: 2026-06-16 Status: architecture audit, no implementation yet Scope: Flue as a possible agent harness and third-party connector layer for OpenAgents product, private workspaces, operator workflows, and launch/business operations. Agent Building agents 446 A 0
75 validationcallstackincubator/rozeniteHow to run checks in this repository without rebuilding all 38 packages for a two-file change. Agent Other 656 A 0
76 FedRAMP & RMF Compliance EngineerSHAdd0WTAka/Zen-Ai-PentestExpert FedRAMP and NIST Risk Management Framework compliance engineer specializing in both FedRAMP authorization pathways — the traditional Rev5 path (NIST 800-53 Rev 5 control implementation, System Security Plans, 3PAO assessment, agency authorization) and the modernized FedRAMP 20x path (Key Security Indicators… Agent Legal and compliance 449 A 130
77 INDEXsbhooley/ainativelangIf you are an AI agent that just needs AINL installed into your host stack, do not read these guides. Run the one-step install from the top of ../../AGENTS.md or ../../README.md. Agent Building agents 671 A 0
78 plinth-tech-leadjabrena/plinthTech lead for Java Enterprise Development. Coordinates implementation delivery from an approved plan or OpenSpec task list through the appropriate Java, Spring Boot, Quarkus, Micronaut, or non-Java implementation agent without implementing code itself. Agent Languages 435 A 52
79 researcherkdcokenny/ocxKnowledge architect for external research and documentation. Agent Research 938 A 7
80 megatron-expertredai-infra/RelaxAn expert assistant for integrating and configuring Megatron, a system for training very large machine-learning models across multiple processors or machines. Agent Data and AI 580 A 29
81 agentsdavidmigloz/langchain_dartSome applications require a flexible chain of calls to LLMs and other tools based on user input. The Agent interface provides the flexibility for such applications. An agent has access to a suite of tools, and determines which ones to use depending on the user input. Agents can use multiple tools, and use the output… Agent Building agents 687 A 0
82 reviewerduckbugio/flockRead-only adversarial reviewer. Pre-PR it returns a verdict for the arbiter; on an open PR it posts true line-anchored INLINE comments via the git-host API, written in the PR's own language. Scores risk and checks cross-service compatibility. Never edits code. Agent Code review 505 A 60
83 sdd-applyGentleman-Programming/gentle-piImplement SDD tasks with strict TDD evidence and review workload guard. Agent Testing 415 A 19
84 TheGardnerdelorenj/mcp-server-trelloProduct manager for @delorenj/mcp-server-trello. Finds and defends the encapsulated workflows that make this server worth installing over the official Atlassian one — judgment made reusable, not endpoints wrapped. Use to evaluate a feature idea/issue/PR against the doctrine, decide what ships next, kill a… Agent Project management 437 A 143
85 instruction-loadingUndertone0809/rudderRudder must assemble each runtime agent's instruction frame from three kinds of truth before invoking the provider. Agent Building agents 288 A 0
86 issue-trackermodernweb-dev/rocketIssues and PRDs for this repo live as markdown files in .scratch/. Agent Project management 394 A 0
87 CHEATSHEETcognesy/instructor-phpAgent loop, state model, tools, context management, hooks, and subagent orchestration. Agent Memory and context 326 A 18
88 legal-risk-reviewcbrock84/headcountReviewer-class. Read-only review of what other departments commit to — contract terms, privacy and data handling, risk acceptance, and compliance findings. Holds no write surface. Its findings are not overrulable by the department under review. Agent Legal and compliance 1.2k A 50
89 checkEpiskey-G/GrokSearch-rsCode quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs and reports findings. Reports only — does not edit code. Agent Code review 440 A 35
90 ralph-auditerJosverl/micropython-stubsUse when auditing and improving all stubs under reference/micropython by iterating module-by-module, invoking Stub Source Auditor for each module, committing each accepted change to auditupdate, and recording durable learnings in repo memory. Agent Git and workflow 317 A 52
91 education-expert-deepadcontextprotocol/adcpCurriculum designer for ad tech education and certification. Builds learning paths for marketers, agencies, and specialists. Expert in multi-modal async learning, assessment design, AI-powered teaching (agent tutors, adaptive learning, generative exercises), and making protocol concepts accessible to non-technical… Agent Learning and teaching 242 A 62
92 quality-assuranceagents-universe/agents-universeBusiness-oriented QA agent – verify user and business outcomes, design and run automated tests, preserve execution evidence, report concise Jira results. Agent Testing 260 A 26
93 deck-creatorai-analyst-lab/ai-analystAgent "deck-creator" from ai-analyst-lab/ai-analyst, covering agent: deck creator, purpose, inputs, non-negotiable defaults and theme selection (critical). Agent Creative and media 296 A 0
94 reviewmicrosoft/Agents-for-netLocal reviewer-vs-challenger loop that reproduces the GitHub Copilot PR review dynamic before you open the PR. Invokes reviewer-github (a different model) to emulate GitHub's findings, then disputes or resolves each one, giving a per-finding verdict — Fix / Push back / Needs judgment. Read-only. Agent Code review 177 A 69
95 READMEluanmorenommaciel/agentspecAgentSpec deploys 58 specialized agents across 8 categories, each built on a three-tier template system with mandatory KB-First knowledge resolution. Every agent carries a cognitive framework that enforces structured confidence scoring, provenance tracking, and explicit stop conditions -- turning raw LLM capability… Agent Building agents 245 A 0
96 logsRamilito/kubectl.nvimPod logs feature specialist. ALWAYS use for ANY task involving log streaming, tailing, JSON toggle, histogram, or LogSession. Agent Debugging 537 A 28
97 job-lifecyclestrelov1/freehireThe open/closed state of a job row, the four mechanisms that write closedat, and the filtering semantics that depend on it. Agent Other 591 A 0
98 create-studymicrosoft/P.808Creates subjective speech quality tests using the P.808 toolkit — handles study setup, gold/trapping clip generation, storage upload, project building for crowdsourcing platforms, prompts for study-specific screen-out completion codes (never reused across studies) and for the internal-vs-general master-script assets… Agent Scientific 230 A 79
99 solve engineering taskequinor/neqsimSolves process-engineering problems using the NeqSim Java API with proportional depth: quick answer-first calculations, notebook-backed studies, or full reports. Delivers auditable task folders with validation evidence, runner-executed notebooks/scripts, and reports when needed. When NeqSim lacks a needed capability… Agent Scientific 150 A 73
100 python-qualitybdfinst/agentic-dev-teamPython code quality — type hints, exception handling, modern idioms, dataclass/Pydantic patterns. Agent Languages 280 A 23

Want everything, not just what passes the gates? Browse all agents. This shelf recomputes nightly from the measurements.