AgentSidekick

Agent SDKs

Code and no-code frameworks for building agents. As of 2026-11-21, 401 indexed products match this subcategory (334 with full profiles); 66 were published in the last 90 days, against 55 in the 90 days before, slower than the catalogue as a whole. By GitHub stars, MarkItDown leads, holding 9% of the stars of the 385 products here with their own repository. The most common form is Frameworks (47% of indexed products).

SubcategorySegment label: Lagging the catalogue DER

Segment statistics

Whole catalogue (all 401 indexed products, not only profiled ones). Calculated 2026-11-21.

401DERIndexed products334 with full profiles
66DERLaunched, last 90 days55 in the 90 days before
13DERMomentum vs catalogue50 = same pace as the catalogue
9%DERLargest project's share of starsAcross 385 products with their own repository
0.036DERConcentration (HHI)About 28 equal-sized projects’ worth; unconcentrated
297SRCMedian starsPer product with its own repository
85%DEROpen sourceMarked open source; unknown counts as not

Lagging the catalogue. Mid-sized for its level, with launches growing more slowly than the catalogue’s. Size is ranked against the other subcategory nodes; momentum compares this node’s launches in the last 90 days with the 90 before, relative to the whole catalogue’s ratio (score 62 or more = faster, 38 or less = slower; below 5 dated launches it is not measured and the label uses size alone).

Concentration. The Herfindahl–Hirschman index (HHI) adds up each project’s squared share of stars. At 0.036, attention is spread as if across about 28 equally popular projects. Using the common competition-policy thresholds (0.15 and 0.25), that is unconcentrated. Stars measure attention, not usage or quality.

Which product forms serve it

The same need is met by MCP servers, agent skills, plugins, extensions and frameworks. This counts each form across the whole catalogue.

Products in Agent SDKs by product type, as of 2026-11-21
Product type IndexedShareWith a profile
Frameworks18846.9%181
MCP servers12932.2%72
Agent skills205.0%20
Libraries164.0%15
Infrastructure153.7%15
Plugins82.0%6
Agent SDKs71.7%7
Agent projects71.7%7
Developer tools41.00%4
Platforms30.75%3
Automation platforms20.50%2
SaaS products10.25%1
Rules packs10.25%1

3 capabilities

Indexed = whole catalogue; profiled = products with their own page. A product can sit in several, so the rows do not add up to the total.

CapabilityIndexed ProfiledNew, 90 daysLabel
Python Agent FrameworksAgent frameworks for Python.755418Established
No-code Agent BuildersVisual tools for assembling agents without code.27175Thin
TypeScript Agent FrameworksAgent frameworks for TypeScript and JavaScript.25148Thin

Top 40 products by GitHub stars

Search the directory

Profiled products only (334 of 401), ranked by the stars of their own repository. Products that live in a subfolder of a larger repository (common for skills) show that whole repository's stars and are ranked after them; products without a repository come last. Stars are popularity, not quality or installs.

Agent SDKs: top profiled products by GitHub stars, 2026-11-21
#ProductTypePublisherCapabilities GitHub stars Last push LicenceSave and compare
1MarkItDownPython utility that converts PDF, Office, HTML, images and audio files into Markdown for LLM consumption.Librarymicrosoft197k14d agoMIT
2DifyPlatform for building LLM apps and agent workflows visually with RAG pipelines, model management and app publishing.Automation platformLangGenius162ktodayLicenseRef-Dify-Open-Source-License
3LangflowVisual builder for agent and RAG flows using drag-and-drop components, with flows deployable as APIs or MCP servers.Automation platformDataStax157ktodayMIT
4claude-memPersistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + MoreAgent skillthedotmack119ktodayApache-2.0
5RAGFlowSelf-hostable RAG engine with deep document parsing, template-based chunking, citations and an agent builder.Frameworkinfiniflow94k1d agoApache-2.0
6OpenHandsOpen-source platform for AI coding agents comprising a Python Software Agent SDK and Agent Server, the Agent Canvas browser client, and a managed OpenHands Cloud with GitHub, GitLab, Slack and Jira integrations.PlatformOpenHands (All Hands AI)94ktodayMIT
7ai-agents-for-beginners18 Lessons to Get Started Building AI AgentsAgent projectmicrosoft81k4d agoMIT
8AutoGenFramework for multi-agent conversations and event-driven agent systems that popularised conversable-agent patterns.Frameworkmicrosoft62k9d agoCC-BY-4.0
9LlamaIndexFramework for building agents and workflows over your data, with connectors, indexing, retrieval and an event-driven Workflows engine.FrameworkLlamaIndex53k1d agoMIT
10nanobotYour lightweight open-source personal agent.MCP serverHKUDS50ktodayMIT
11AgnoPython framework and runtime for agents and multi-agent teams with memory, knowledge and a production API server (AgentOS).FrameworkAgno43k1d agoApache-2.0
12BettaFish微舆:人人可用的多Agent舆情分析助手,打破信息茧房,还原舆情原貌,预测未来走向,辅助决策!从0实现,不依赖任何框架。Framework666ghj43k1mo agoGPL-2.0
13DSPyFramework for programming LM pipelines as declarative modules with signatures, then compiling them with optimisers that tune prompts and weights against metrics.FrameworkStanford NLP39k2d agoMIT
14AgentScopePython multi-agent framework with message-based agent communication, tool use, memory and a visual studio for debugging.FrameworkAlibaba (AgentScope)36k1d agoApache-2.0
15CuaOpen-source infrastructure for computer-use agents: sandboxed macOS, Linux and Windows VMs plus an agent SDK.InfrastructureCua33ktodayMIT
16OpenAI Agents SDKLightweight SDK for multi-agent workflows with agents, handoffs, guardrails, sessions and built-in tracing; works with OpenAI and other model providers.SDKopenai31ktodayMIT
17smolagentsMinimal Python library for agents that write and execute Python code as their actions, with sandboxed execution options and Hub integration.LibraryHugging Face30k1d agoApache-2.0
18MastraTypeScript framework for agents, workflows, RAG, memory and evals, with a local dev playground and deploy targets for common hosts.FrameworkMastra30ktodayApache-2.0
19AI SDKTypeScript toolkit providing a unified API across model providers for text generation, structured output, tool calling and agent loops, plus React/Svelte/Vue UI hooks for streaming chat.SDKvercel28ktodayApache-2.0
20HaystackPython framework for composing pipelines and agents from components for retrieval, generation and tool use, aimed at production RAG and search.Frameworkdeepset27ktodayApache-2.0
21awesome-claude-code-subagentsA collection of 100+ specialized Claude Code subagents covering a wide range of development use casesAgent projectVoltAgent27k19d agoMIT
22Agent Development Kit (ADK)Code-first toolkit for building, evaluating and deploying single and multi-agent systems, optimised for Gemini and Google Cloud but model-agnostic.SDKgoogle22ktodayApache-2.0
23agents-towards-productionEnd-to-end, code-first tutorials for building production-grade GenAI agents. From prototype to enterprise deployment.FrameworkNirDiamant22k6d ago—
24Pydantic AIType-safe Python agent framework built around Pydantic validation, dependency injection, structured outputs and graph-based control flow.Frameworkpydantic21ktodayMIT
25rocketride-serverRocketRide is an open source AI meta-harness with the only enterprise-grade runtime built on C++. Build, test and publish durable agents that scale in production.MCP serverrocketride-org20ktodayMIT
26openfangOpen-source Agent Operating SystemFrameworkRightNow-AI18k4mo agoApache-2.0
27CAMELMulti-agent framework for role-playing agent societies, synthetic data generation and large-scale agent simulations.Frameworkcamel-ai18k5d agoApache-2.0
28SuperAGI<⚡️> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably.InfrastructureTransformerOptimus18k1y agoMIT
29Trigger.devBackground job and durable task platform for TypeScript with retries, queues and realtime run updates, often used for agents.InfrastructureTrigger.dev17ktodayApache-2.0
30eigentEigent: The Open Source Cowork Desktop - Local and Free Alternative to Claude Cowork and CodexAgent skilleigent-ai16k1d agoApache-2.0
31Arize PhoenixSelf-hostable tracing and evaluation tool built on OpenTelemetry/OpenInference for inspecting LLM and agent runs, datasets and experiments.Developer toolArize-ai12ktodayElastic-2.0
32omnigentOmnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.Frameworkomnigent-ai11ktodayApache-2.0
33xiaozhi-esp32-server本项目为xiaozhi-esp32提供后端服务,帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.MCP serverxinnan-tech11k2d agoMIT
34hiveMulti-Agent Harness for Production AIAgent skilladen-hive11k4d agoApache-2.0
35VoltAgentTypeScript agent framework with memory, workflows, supervisor/sub-agent patterns and a companion observability console.FrameworkVoltAgent11k15d agoMIT
36PraisonAIAI Agents Framework with Self Reflection and MCP supportMCP serverMervinPraison9.4k1d agoMIT
37Strands AgentsModel-driven agent SDK where the model plans and calls tools in a loop; supports Amazon Bedrock and other providers and deploys to AWS services.SDKAmazon Web Services9.3k1d agoApache-2.0
38evolverThe GEP-powered self-evolving engine for AI agents. Auditable evolution with Genes, Capsules, and Events. | evomap.aiFrameworkEvoMap8.7k1d agoGPL-3.0
39Claude Agent SDKSDK that exposes the agent loop behind Claude Code (file and shell tools, subagents, hooks, permissions, context compaction) for building custom agents in Python or TypeScript.SDKAnthropic8.6ktodayMIT
40MiroThinkerMiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.FrameworkMiroMindAI8.5k4mo agoApache-2.0

Most common integrations

Third-party services named by products in this node, whole catalogue.

IntegrationProducts Share
n8n51.2%
Azure41.0%
GitHub41.0%
Kubernetes41.0%
Vercel41.0%
PostgreSQL30.7%
AWS20.5%
Android20.5%
Slack20.5%
Stripe20.5%
Chroma10.2%
Discord10.2%
GitLab10.2%
Google Calendar10.2%
Google Cloud10.2%

Launches per month

New Agent SDKs products per monthSRC

Whole catalogue, by publication month, 2024-11 to 2026-11. The last month is partial; undated products are excluded.

New Agent SDKs products per monthWhole catalogue, by publication month, 2024-11 to 2026-11. The last month is partial; undated products are excluded.. Products published: 25 points, latest 12 products in 2026-11.
Show the data as a table
New Agent SDKs products per month. Whole catalogue, by publication month, 2024-11 to 2026-11. The last month is partial; undated products are excluded.
Products published (products)
2024-112
2024-126
2025-018
2025-024
2025-032
2025-048
2025-056
2025-066
2025-079
2025-089
2025-099
2025-106
2025-113
2025-125
2026-015
2026-0233
2026-0338
2026-0427
2026-0522
2026-0616
2026-0721
2026-0824
2026-0925
2026-1022
2026-1112

Related opportunities

Opportunity radar

Scored gaps for this node or anything beneath it. Scores rank hypotheses; they do not predict demand.

OpportunityCompetitionConfidenceScore
Coverage gap: TypeScript Agent FrameworksTypeScript Agent FrameworksHighLow59.6
Coverage gap: No-code Agent BuildersNo-code Agent BuildersHighLow59.2
Coverage gap: Python Agent FrameworksPython Agent FrameworksHighLow53.4

Limits of these numbers

  • Products are placed here by whole-word keyword rules on their name, description and repository topics, and inherit every ancestor of a matched node. Products that do this without naming it are missed; ambiguous words cause false matches. Methodology
  • About half of the catalogue matches no node at all, so absolute counts understate every category.
  • Launch counts use the publication date each source reports; for auto-discovered repositories that is the repository’s creation date.
  • Stars and concentration cover only products with their own repository (not a subfolder of a larger one). They measure attention, not adoption.

Page data last updated .