Agent Security
Identity, access, governance and threat protection for agents. As of 2026-11-21, 1,481 indexed products match this category (469 with full profiles); 650 were published in the last 90 days, against 368 in the 90 days before, slower than the catalogue as a whole. By GitHub stars, iFixAi leads, holding 9% of the stars of the 1,110 products here with their own repository. The most common form is MCP servers (85% of indexed products).
CategorySegment label: Lagging the catalogue DER
Segment statistics
Whole catalogue (all 1,481 indexed products, not only profiled ones). Calculated 2026-11-21.
Lagging the catalogue. Mid-sized for its level, with launches growing more slowly than the catalogue’s. Size is ranked against the other category 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 0.033, attention is spread as if across about 31 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.
| Product type | Indexed | Share | With a profile |
|---|---|---|---|
| MCP servers | 1,261 | 85.1% | 268 |
| Agent skills | 62 | 4.2% | 62 |
| Plugins | 51 | 3.4% | 43 |
| Infrastructure | 45 | 3.0% | 45 |
| Libraries | 18 | 1.2% | 15 |
| Frameworks | 14 | 0.95% | 14 |
| Rules packs | 12 | 0.81% | 4 |
| Agent projects | 6 | 0.41% | 6 |
| SaaS products | 4 | 0.27% | 4 |
| Developer tools | 3 | 0.20% | 3 |
| AI APIs | 2 | 0.14% | 2 |
| Agent SDKs | 1 | 0.07% | 1 |
| Protocols & standards | 1 | 0.07% | 1 |
| Automation platforms | 1 | 0.07% | 1 |
3 subcategories
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.
| Subcategory | Indexed | Profiled | New, 90 days | Label |
|---|---|---|---|---|
| Agent GovernanceHuman oversight, audit and policy for agent actions. | 724 | 230 | 317 | Lagging the catalogue |
| Agent Threat ProtectionDefending agents from injection, poisoned tools and leaks. | 473 | 138 | 213 | Lagging the catalogue |
| Agent Identity & AccessWho an agent is and what it may touch. | 439 | 159 | 189 | Lagging the catalogue |
Top 40 products by GitHub stars
Search the directoryProfiled products only (469 of 1,481), 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.
| # | Product | Type | Publisher | Capabilities | GitHub stars | Last push | Licence | Save and compare |
|---|---|---|---|---|---|---|---|---|
| 1 | iFixAiIndependent Auditing of AI Agents. Run by human or the agent itself, to answer the most crucial question in the AI Agent Economy. Is the agent doing what is supposed to do? With iFixAi you can have this answer in less than 120 seconds. | Infrastructure | ifixai-ai | 47k | 1d ago | Apache-2.0 | ||
| 2 | LangGraphLow-level orchestration framework that models agents as stateful graphs with checkpointing, human-in-the-loop interrupts and durable execution. | Framework | LangChain | 45k | today | MIT | ||
| 3 | OpenAI Agents SDKLightweight SDK for multi-agent workflows with agents, handoffs, guardrails, sessions and built-in tracing; works with OpenAI and other model providers. | SDK | openai | 31k | today | MIT | ||
| 4 | infisicalInfisical is the open-source platform for securing secrets, certificates, access, and AI Agents. | Agent project | Infisical | 31k | today | — | ||
| 5 | nocobaseNocoBase is the open-source platform for building, running, and evolving business systems with AI. Agents write the code and do the work, NocoBase provides the foundation and governance, and people make the decisions. | Agent skill | nocobase | 25k | today | — | ||
| 6 | mcp-for-beginnersThis open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable, and secure AI workflows from session setup to service orchestration. | MCP server | microsoft | 18k | today | MIT | ||
| 7 | TREKThe most complete open-source travel planner: real-time collaboration, bookings, budgets, packing lists, journals, offline PWA, SSO and an AI-ready MCP server, with planet-wide place search and routing built in. | MCP server | liketrek | 16k | today | AGPL-3.0 | ||
| 8 | OmniGetDesktop toolbox for coding agents: downloads, files, pages, ports, chats and cleanup, in OmniGet | MCP server | tonhowtf | 15k | 1d ago | GPL-3.0 | ||
| 9 | Portkey AI GatewayGateway that routes requests to many LLM providers with retries, fallbacks, load balancing, caching and guardrails; open-source core plus hosted control plane. | Infrastructure | Palo Alto Networks (Portkey) | 13k | 1d ago | MIT | ||
| 10 | bishengBISHENG is an open-source enterprise Agent platform for building, deploying, and managing AI applications. It combines AI agents, workflows, RAG and knowledge management, desktop agent integration, and vibecoding app hosting with unified model management, evaluation, observability, access control, and enterprise administration. | Infrastructure | dataelement | 12k | 1d ago | Apache-2.0 | ||
| 11 | fastapi_mcpExpose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth! | MCP server | tadata-org | 12k | 12mo ago | MIT | ||
| 12 | hiveMulti-Agent Harness for Production AI | Agent skill | aden-hive | 11k | 4d ago | Apache-2.0 | ||
| 13 | garakLLM vulnerability scanner that probes models and apps for jailbreaks, prompt injection, data leakage and toxicity. | Developer tool | NVIDIA | 10k | 3d ago | Apache-2.0 | ||
| 14 | failproofaiObservability and enforcement for AI agent harnesses. Capture every run and runtime reliability with policy enforcement. | Infrastructure | FailproofAI | 9.9k | today | — | ||
| 15 | BifrostGo-based LLM gateway exposing many providers through one OpenAI-compatible API with failover, load balancing, governance and an MCP gateway. | Infrastructure | Maxim AI | 9.9k | today | Apache-2.0 | ||
| 16 | Model Context Protocol (MCP)Open JSON-RPC protocol that lets AI applications connect to external tools, resources and prompts exposed by MCP servers over stdio or HTTP. Defines client/server capabilities, authorization and transport rules. | Protocol | Agentic AI Foundation (Linux Foundation) | 9.7k | today | MIT AND Apache-2.0 | ||
| 17 | Guardrails AIPython framework that wraps LLM calls with input/output validators from a hub to detect PII, toxicity, jailbreaks and schema violations. | Library | Guardrails AI | 7.6k | 3d ago | Apache-2.0 | ||
| 18 | AI-Infra-GuardA full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation. | Infrastructure | Tencent | 7.6k | 1d ago | Apache-2.0 | ||
| 19 | NeMo GuardrailsToolkit for adding programmable rails (topic control, jailbreak and content safety checks) to LLM apps using the Colang language. | Library | NVIDIA | 7.5k | 2d ago | Apache-2.0 | ||
| 20 | planoPlano is an AI-native proxy server and data plane for agentic apps. Smart LLM routing, observability, agent orchestration, and guardrails so you stay focused on your agents core logic. | Infrastructure | katanemo | 7.1k | 28d ago | Apache-2.0 | ||
| 21 | agent-governance-toolkitAI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10. | Framework | microsoft | 6.6k | today | MIT | ||
| 22 | bla🛡️ BLA (bla-agents / Blind LLM Agents) — Open-source Blue Defense MCP server & CLI protecting JS/TS, Electron ASAR, WASM, Python, Native Binaries, SQLite, GGUF/Safetensors & Android DEX against AI reverse-engineering agents (REA). | MCP server | qybaihe | 6.4k | today | MIT | ||
| 23 | agentgatewayRust data plane for agent traffic that proxies MCP, A2A and LLM calls with authentication, authorisation policies and telemetry. | Infrastructure | Linux Foundation | 6.3k | today | Apache-2.0 | ||
| 24 | SoduWorkThe AI-native engine for teams and their agents. Multi-harness, multi-agent, self-hosted. | Agent project | mdiri-ai | 6.2k | today | MIT | ||
| 25 | GiskardTesting library that scans LLM agents and RAG apps for hallucination, prompt injection and harmful-content vulnerabilities and generates test suites. | Library | Giskard | 6.0k | 1d ago | Apache-2.0 | ||
| 26 | skillhubSelf-hosted, open-source agent skill registry for enterprises. Publish & version skill packages, govern with RBAC and audit logs, deploy on-premise with Docker or Kubernetes. | Framework | iflytek | 5.4k | 1d ago | Apache-2.0 | ||
| 27 | LoopForgeSelf-hosted workflows for coding-agent delivery. Orchestrate CodeBuddy, Codex and Claude Code with scripts and human approval gates. Includes Local workflows for coding assistants. | Agent project | Tencent | 5.4k | today | — | ||
| 28 | Handsy AILet AI agents see and operate a real iPhone via an ESP32-S3 USB HID + AirPlay. No jailbreak. | MCP server | onehumanbeing | 5.2k | today | MIT | ||
| 29 | nonoagent runtime security - zero trust, zero setup, zero latency agent sandboxing | Agent project | nolabs-ai | 5.1k | 1d ago | Apache-2.0 | ||
| 30 | PyRITPython Risk Identification Tool for automated red-teaming of generative AI systems with attack orchestrators and scorers. | Developer tool | microsoft | 5.0k | today | MIT | ||
| 31 | ContextForge MCP GatewayGateway and registry that federates MCP servers, A2A agents and REST APIs behind one endpoint with auth, rate limiting and observability. | Infrastructure | IBM | 4.9k | 1d ago | Apache-2.0 | ||
| 32 | daguSelf-hostable workflow orchestrator for teams whose main work isn't orchestration. Declarative YAML over your scripts, SSH commands, containers, etc; keep workflows separate from business logic. One binary, no database, runs on limited H/W resources. Alternative to Airflow / Cron / Job Scheduler. | MCP server | dagucloud | 4.6k | today | GPL-3.0 | ||
| 33 | archestraEnterprise AI Platform with guardrails, MCP registry, gateway & orchestrator | MCP server | archestra-ai | 4.5k | today | — | ||
| 34 | Radar Kubernetes MCP ServerKubernetes MCP server for diagnosis, resource management, GitOps, and RBAC-enforced operations. | MCP server | skyhook-io | 4.2k | today | Apache-2.0 | ||
| 35 | stop-that-shitStop That Shit(别再造史了)|面向 Codex/GPT 场景的多平台 Hook + Skill Guard:拦截 AI coding agent 无需求的哈希、校验和与任务范围膨胀。 A multi-platform Hook + Skill Guard for AI coding agents in Codex/GPT workflows: stop unrequested hashes, checksums, and task-scope creep. | Agent skill | lennney | 4.0k | 2d ago | MIT | ||
| 36 | lean-ctxLeanCTX is the Context Gateway for AI Systems. Select task-relevant context, apply supported controls, connect local knowledge and inspect recorded evidence. Open-source Engine: CLI, MCP, hooks and supported proxy paths. | MCP server | yvgude | 4.0k | 3d ago | Apache-2.0 | ||
| 37 | AI-Engineer-HeadquartersA collection of scientific methods, processes, algorithms, and systems to build stories & models. | Infrastructure | hemansnation | 3.8k | 24d ago | — | ||
| 38 | Snyk Agent ScanScanner that inspects installed MCP servers and agent configs for tool poisoning, prompt injection and toxic flows. | Developer tool | Snyk (Invariant Labs) | 3.3k | 2d ago | Apache-2.0 | ||
| 39 | teaql-agent-kitA model-driven harness for AI coding agents: semantic modeling, app generation, progressive API Assist and evidence-based verification. | Agent project | teaql | 2.8k | 11d ago | MIT | ||
| 40 | Deep-Research-skillsStructured deep research skill for Claude Code/Open Code/Codex with human-in-the-loop control | Agent skill | Weizhena | 2.6k | 3mo ago | MIT |
Most common integrations
Third-party services named by products in this node, whole catalogue.
| Integration | Products | Share |
|---|---|---|
| GitHub | 16 | 1.1% |
| PostgreSQL | 15 | 1.0% |
| Kubernetes | 14 | 0.9% |
| AWS | 9 | 0.6% |
| Gmail | 9 | 0.6% |
| Telegram | 8 | 0.5% |
| MySQL | 7 | 0.5% |
| YouTube | 7 | 0.5% |
| 6 | 0.4% | |
| Android | 5 | 0.3% |
| Azure | 5 | 0.3% |
| Google Cloud | 4 | 0.3% |
| Obsidian | 4 | 0.3% |
| Slack | 4 | 0.3% |
| Solana | 4 | 0.3% |
Launches per month
New Agent Security products per monthSRC
Whole catalogue, by publication month, 2024-11 to 2026-11. The last month is partial; undated products are excluded.
Show the data as a table
| Products published (products) | |
|---|---|
| 2024-11 | 1 |
| 2024-12 | 2 |
| 2025-01 | 1 |
| 2025-02 | 3 |
| 2025-03 | 6 |
| 2025-04 | 6 |
| 2025-05 | 6 |
| 2025-06 | 1 |
| 2025-07 | 2 |
| 2025-08 | 1 |
| 2025-09 | 10 |
| 2025-10 | 8 |
| 2025-11 | 6 |
| 2025-12 | 5 |
| 2026-01 | 15 |
| 2026-02 | 39 |
| 2026-03 | 71 |
| 2026-04 | 91 |
| 2026-05 | 83 |
| 2026-06 | 90 |
| 2026-07 | 144 |
| 2026-08 | 146 |
| 2026-09 | 174 |
| 2026-10 | 257 |
| 2026-11 | 187 |
Related opportunities
Opportunity radarScored gaps for this node or anything beneath it. Scores rank hypotheses; they do not predict demand.
No scored opportunity here
Capability gaps are only scored inside subcategories with at least 20 indexed products, and only the top 80 are kept. None falls under this node.
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 .