PAGES
← all tools
◆ WAF, Bot & API Protection

Akto

Discover Every Plugin Installed to Your AI Agents open-source

Akto discovers APIs, MCPMCPModel Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers and AI agents, tests and red-teams them, and enforces runtime guardrails and posture management.

Summary

Akto is an open-source application security platform that discovers APIs, MCP servers, and AI agents, testing them for vulnerabilities and enforcing runtime guardrails. It requires no cost for use and can be run via a command-line interface. It is intended for practitioners focused on API-security, AI-security, and red-teaming. Its documentation positions it alongside tools for maintaining API inventory and testing for common vulnerabilities. The project launched in 2021.

Akto discovers APIs, MCP servers and AI agents, tests and red-teams them, and enforces runtime guardrails and posture management.

How Akto helps

Which APIs, MCP servers, and AI agents are actually running in my environment right now?

crawls traffic and configuration to build a live inventory, surfacing services nobody documented or remembered to register

Which of my APIs are exposed to an OWASP Top 10 category of vulnerability?

runs its test suite against discovered endpoints and reports which ones fail which category, tied to the specific request that triggered the failure

Would my AI agent leak data or take an unsafe action if someone tried to manipulate it?

red-teams the agent with adversarial prompts and records which attempts got through and what the agent did in response

Which runtime traffic is violating the guardrails I've set, right now?

watches live requests against configured policies and flags the ones that break a rule, naming the endpoint and the rule it broke

Is my API inventory drifting from what my security policy assumes it covers?

continuously reconciles discovered endpoints against the tracked inventory, so newly-seen or newly-changed APIs surface instead of aging silently untested

all 21 features, with the evidence for each →

Languages

Not documented

Features

21 capabilities

Built from Akto's releases, docs, README and our own runs. “Seen” marks the month we first spotted a release the vendor didn't date. Group names and tags are our labels.

Compare with peers →

What Akto offers you

  • Command-line interface3
  • Built-in AI assistant1
  • CI/CD pipeline integration1
  • ML-based detection1
  • Role-based access control1
  • Scripting API1
  • Scripting language support1
  • Single sign-on1
  • Ticketing integration1
All capabilities 21 capabilities
API inventory and vulnerability testing shipped Maintains an inventory of APIs and tests them for vulnerabilities across OWASP top 10 categories, including runtime issue detection, via both a platform interface and a CLI tool. 43 releases · 5 other sources · first seen Mar 2023

Also counts toward: Command-line interface

release 43 total

  • Adds Tool Invocation Visibility in AI Red Teaming to view tools agents invoked during probe execution. Guardrails for Every AI Coding Workflows · Apr 2026 · source · release history
  • Extended Timeout limit allows longer agentic red teaming scans for complex multi-step LLM interactions Full AI Security Posture for Endpoints in Akto Atlas · Mar 2026 · source · release history
  • Bulk Scan AI Agent Groups enables running security scans against multiple grouped agents simultaneously Full AI Security Posture for Endpoints in Akto Atlas · Mar 2026 · source · release history
  • Google AI ADK integration enables security, probing, and guardrail enforcement for Google AI agent workflows Full AI Security Posture for Endpoints in Akto Atlas · Mar 2026 · source · release history
  • Run bulk Red Teaming across multiple AI Agents and MCPs with consolidated results. Complete Observability Into your AI Agents · Feb 2026 · source · release history
  • Vertex AI Integration discovers and secures agents running on Google Vertex AI. Complete Observability Into your AI Agents · Feb 2026 · source · release history

docs

  • Open source API security platform for maintaining API inventory, testing APIs for vulnerabilities, and finding runtime issues across OWASP top 10 categories.

example

  • Download a report of identified API vulnerabilities directly from the UI. Steps: In the Akto dashboard, navigate to the Vulnerabilities section and select 'Download Report'. v1.41.7 · Jul 2024 · source
  • Create a test case specifically designed to check if cookie expiration logic is correctly validated during API requests. Navigate to Test Editor > Add New Test > Select 'cookie expiry tests' from the available templates. v1.34.10 · Jan 2024 · source
  • Run a new test case to detect JWT auth bypass via JWK header injection within the Akto service UI. Navigate to Test Editor > Add New Test > Select 'jwt authentication bypass via jwk header injection' as the test type. v1.34.10 · Jan 2024 · source
  • Run API tests via CLI tool docker run -v ./:/out \
Guardrail Policy Engine and Enforcement shipped Defines, validates, and enforces configurable guardrail policies on inputs and outputs for AI agents in real-time across various CLI hooks, SDKs, and platforms. 38 releases · first seen Jan 2026

Also counts toward: Command-line interface

release 38 total

  • Provides a reference architecture for a Claude Code → LiteLLM → Bedrock → Anthropic deployment with layered Akto guardrails at github.com/akto-api-security/akto-litellm. announced · seen Oct 2026 · source · release history
  • Adds guardrail: akto as a native LiteLLM guardrail provider, configured via guardrail_name, akto_base_url (os.environ/AKTO_GUARDRAIL_API_BASE), and akto_api_key (os.environ/AKTO_API_KEY) in config.yaml.⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ announced · seen Oct 2026 · source · release history
  • Implements Statistical Anomaly Guardrails to detect behavior drift and tool misuse by baselining normal usage per agent. Discover Every Plugin Installed to Your AI Agents · Aug 2026 · source · release history
  • Intercepts Amp proxy traffic to apply guardrail policies through Akto for Amp-based coding agents. Discover Every Plugin Installed to Your AI Agents · Aug 2026 · source · release history
  • Adds a Glean Connector to enforce guardrail policies on employee interactions with Glean's AI agents and capture full traces. Discover Every Plugin Installed to Your AI Agents · Aug 2026 · source · release history
  • Acts as the AI security server for Anthropic's Inference Hooks, providing allow/deny verdicts for claude.ai, Cowork, and Claude Code. Discover Every Plugin Installed to Your AI Agents · Aug 2026 · source · release history
Agentic Inventory and Discovery shipped Discovers, maps, and manages AI agents, MCP servers, and related skills across diverse platforms including endpoints, cloud providers, and developer environments. 30 releases · first seen Jan 2026

release 30 total

  • Maps Copilot Studio agents to connected tools, topics, MCP servers, and knowledge sources in an architecture view. Discover Every Plugin Installed to Your AI Agents · Aug 2026 · source · release history
  • Surfaces all plugins installed to AI agents, including skills, MCP servers, and bundled tools. Discover Every Plugin Installed to Your AI Agents · Aug 2026 · source · release history
  • Groups SaaS-based AI agents separately under SaaS Agents in the inventory. Discover Every Plugin Installed to Your AI Agents · Aug 2026 · source · release history
  • Adds a New agentic assets layout beta for browsing AI agents, MCP servers, LLMs, skills, and endpoints. Trace Every Prompt, Tool Call, and Response · Jun 2026 · source · release history
  • Copilot Studio Bot Filtering allows filtering by Bot ID under Argus Connectors Skill Governance Across Every AI Agent · May 2026 · source · release history
  • Adds Skills Inventory and Blocking to discover agent skills and block risky ones in bulk or per-endpoint. Guardrails for Every AI Coding Workflows · Apr 2026 · source · release history
Advanced Test Execution Engine shipped Provides a powerful test execution environment supporting dynamic request construction, token manipulation, and complex scripting logic. 24 releases · 2 other sources · first seen Jun 2023

Also counts toward: Scripting API, Scripting language support

release 24 total

  • Shows the full scope of MCP and agent servers a policy touches before deployment in the Apply to All view. Trace Every Prompt, Tool Call, and Response · Jun 2026 · source · release history
  • Domain-Based Proxy Routing routes AI domains through proxy while chatty domains bypass it Skill Governance Across Every AI Agent · May 2026 · source · release history
  • eq, neq obj comparison filters added v1.53.8 · Jan 2025 · source · release history
  • Adds query params support via payload keys in configs to allow mapping request parameters directly from payloads. v1.53.6 · Jan 2025 · source · release history
  • modify multiple auth tokens enables updating or refreshing several authentication tokens in a single operation. v1.38.5 · May 2024 · source · release history
  • Added support for testing graphql APIs in test editor v1.38.1 · May 2024 · source · release history

example

  • Filter API findings to show only those where a specific object field matches or differs from a value. filter obj.field eq 'expected_value' v1.53.8 · Jan 2025 · source
  • Use the execute block to dynamically construct API requests for complex testing scenarios. execute { // New features allow dynamic request building } v1.34.4 · Jan 2024 · source
AI Red Teaming and Probing shipped Executes security probes, red teaming attacks, and vulnerability scans against AI agents and models, supporting various engine configurations and result visualization. 18 releases · first seen Oct 2023

release 18 total

  • Scans settings.json and config.toml on Claude Code, Codex CLI, and Copilot CLI endpoints for misconfigurations like bypassed permissions or disabled sandboxes. Discover Every Plugin Installed to Your AI Agents · Aug 2026 · source · release history
  • Allows scanning by specific attack technique and strategy to target probes at defined threat models. Trace Every Prompt, Tool Call, and Response · Jun 2026 · source · release history
  • Enables red teaming Microsoft Copilot Studio agents using configured OAuth credentials for adversarial probing. Trace Every Prompt, Tool Call, and Response · Jun 2026 · source · release history
  • Multi-LLM Agent Guard runs scanning across multiple LLM providers and model configurations Skill Governance Across Every AI Agent · May 2026 · source · release history
  • Adds Tool Invocation Visibility in AI Red Teaming to view tools agents invoked during probe execution. Guardrails for Every AI Coding Workflows · Apr 2026 · source · release history
  • Adds Category-wise scan scoring to view scan coverage by agentic risk category and pass/fail rates. Guardrails for Every AI Coding Workflows · Apr 2026 · source · release history
User and Feature Management shipped Manages user authentication, feature gating based on pricing plans, and usage data visibility. 16 releases · first seen Mar 2023

release 16 total

  • Adds Custom Roles with Okta SSO support (Admin, Developer, Threat Engineer, Threat Viewer). Guardrails for Every AI Coding Workflows · Apr 2026 · source · release history
  • SSO-Only Login Restrictions enforce consistent authentication by restricting non-SSO logins for SSO-signed-up users Full AI Security Posture for Endpoints in Akto Atlas · Mar 2026 · source · release history
  • Okta Group-to-Role Mapping maps Okta groups to Akto roles (Admin, Member, Developer, Guest) for automatic RBAC during SSO Full AI Security Posture for Endpoints in Akto Atlas · Mar 2026 · source · release history
  • See associated username in guardrail activity on endpoints for better traceability. Complete Observability Into your AI Agents · Feb 2026 · source · release history
  • Export guardrail activity reports to a custom webhook for SIEM or alerting pipeline integration. Complete Observability Into your AI Agents · Feb 2026 · source · release history
  • Enables telemetry collection for the Akto cyber tool. v1.53.7 · Jan 2025 · source · release history
AI Guardrail Policy Controls shipped Enforces configurable guardrail policies for AI usage, including identity-based scoping by email, user, device, and account type, blocks on public sharing of AI chats and artifacts, and a human-in-the-loop approval workflow with recorded decision history for policy violations. 15 releases · first seen Jan 2026

release 15 total

  • Adds identity-based guardrail scoping by email, user, device, and account type. changelog · Oct 2026 · source · release history
  • Adds public-sharing blocks for AI chats and artifacts. changelog · Oct 2026 · source · release history
  • Adds human-in-the-loop approval workflow for AI guardrail policy violations, with every decision recorded in approval history.⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠ changelog · Oct 2026 · source · release history
  • Human-in-the-Loop Overrides for time-bound, logged guardrail event approvals Guardrails for Claude Cowork, Sync and Async · Jul 2026 · source · release history
  • Adds Claude Agent SDK integration to enforce guardrails via native callback system. Guardrails for Every AI Coding Workflows · Apr 2026 · source · release history
  • Adds Codex CLI Hooks to enforce guardrails on prompts, tool calls, and responses in Codex-powered workflows. Guardrails for Every AI Coding Workflows · Apr 2026 · source · release history
API Dependency Mapping shipped Analyzes traffic data to build and visualize a dependency graph of API endpoints. 12 releases · first seen Jan 2024

release 12 total

  • Adds Skills Inventory and Blocking to discover agent skills and block risky ones in bulk or per-endpoint. Guardrails for Every AI Coding Workflows · Apr 2026 · source · release history
  • Adds Host Exclusion Controls in Settings to exclude specific hosts from Traffic Analysis. Guardrails for Every AI Coding Workflows · Apr 2026 · source · release history
  • Agent Details Panel provides User Analysis, MCP Servers, and Agent Logs within Endpoint Shield Full AI Security Posture for Endpoints in Akto Atlas · Mar 2026 · source · release history
  • Salesforce integration connects to instances to discover, monitor, and scan Salesforce API endpoints Full AI Security Posture for Endpoints in Akto Atlas · Mar 2026 · source · release history
  • Agentic Asset Tabs added to the Atlas dashboard to filter agentic assets by type for inventory review Full AI Security Posture for Endpoints in Akto Atlas · Mar 2026 · source · release history
  • View traces and spans directly in agentic workflow details for full request-level observability. Complete Observability Into your AI Agents · Feb 2026 · source · release history
Automated CI/CD Integration shipped Integrates API security testing into continuous integration and deployment pipelines via CLI, GitHub checks, and comments. 9 releases · first seen May 2023

Also counts toward: CI/CD pipeline integration, Command-line interface

release 9 total

  • Introduces the Traces dashboard for LLM observability with Conversation Insights to automatically classify session topics. Trace Every Prompt, Tool Call, and Response · Jun 2026 · source · release history
  • Adds support for sending test run result webhooks to Microsoft Teams v1.54.4 · Feb 2025 · source · release history
  • Adds slack integration to send alerts when API security test runs complete v1.37.22 · May 2024 · source · release history
  • Adds interceptors for Jira integration v1.36.8 · Mar 2024 · source · release history
  • Adds JIRA integration for syncing findings v1.36.5 · Mar 2024 · source · release history
  • Added support to save HAR and Postman files when uploading traffic v1.32.6 · Dec 2023 · source · release history
Guardrail Policy Enforcement and Control shipped Enforces configurable guardrails on inputs, outputs, topics, and file types using statistical anomaly detection and sensitive data redaction. 8 releases · first seen Apr 2026

Also counts toward: ML-based detection

release 8 total

  • Adds model-based (semantic/LLM-driven) PII detection that catches paraphrased, spelled-out, or contextually described PII that regex and Presidio structured-entity recognition cannot match. announced · seen Oct 2026 · source · release history
  • Supports mode: pre_call and mode: post_call guardrail entries for Akto, covering PII scanning on both inbound user prompts and outbound model responses independently. announced · seen Oct 2026 · source · release history
  • Enables default_on: true on individual Akto guardrail entries in config.yaml to enforce PII scanning across all traffic without per-request opt-in. announced · seen Oct 2026 · source · release history
  • Implements Statistical Anomaly Guardrails to detect behavior drift and tool misuse by baselining normal usage per agent. Discover Every Plugin Installed to Your AI Agents · Aug 2026 · source · release history
  • Allows defining sensitive data in plain language for automatic LLM-based redaction before requests reach the model. Discover Every Plugin Installed to Your AI Agents · Aug 2026 · source · release history
  • Adds Default denied topics capability to block off-limits conversations instantly or via custom definitions without building policies from scratch. Trace Every Prompt, Tool Call, and Response · Jun 2026 · source · release history
Risk Scoring shipped Calculates and displays risk scores for APIs based on test results and vulnerability data. 7 releases · first seen Jan 2024

release 7 total

  • Arcade Integration secures Arcade AI agent tool calls with Akto guardrails. Complete Observability Into your AI Agents · Feb 2026 · source · release history
  • Set severity levels in guardrail policies for better prioritization of security alerts. Complete Observability Into your AI Agents · Feb 2026 · source · release history
  • Compliance-Mapped Threat Reports map threats to GDPR, HIPAA, SOC 2 and allow instant export of audit-ready reports. Turning the Lights on for OpenClaw 💡 · Jan 2026 · source · release history
  • Added automated API group creation v1.39.3 · May 2024 · source · release history
  • Add API groups based on risk score allows organizing APIs into groups derived from their aggregate risk metrics. v1.38.5 · May 2024 · source · release history
  • Optimizes calculation of risk score for better performance v1.37.22 · May 2024 · source · release history
Custom Collection Management shipped Allows users to create and organize custom collections of API endpoints for focused testing and analysis. 5 releases · 2 other sources · first seen Jan 2024

release

  • Adds hostname collections for traffic type other v1.40.8 · Jun 2024 · source · release history
  • Adds deactivate collections capability to mark specific API collections as inactive v1.38.4 · May 2024 · source · release history
  • Implemented fine controls for redacting api collections and data types v1.35.5 · Feb 2024 · source · release history
  • Added feature to create custom collections v1.34.9 · Jan 2024 · source · release history
  • Users can create custom collections by adding API endpoints from multiple collections as well as grouped on methods v1.34.7 · Jan 2024 · source · release history

example

  • Create a new collection in the Akto interface to group specific API endpoints for focused monitoring. In the Akto UI, navigate to the Collections section and select 'Create Custom Collection'. v1.34.9 · Jan 2024 · source
  • Create a cross-collection custom collection grouped by HTTP method for focused review. In the Akto console, create a new custom collection and select endpoints from multiple existing collections, grouping them by method. v1.34.7 · Jan 2024 · source
Traffic Capture and Export shipped Captures live API traffic and allows export to standard formats like HAR or Postman for external analysis. 5 releases · 1 other source · first seen Dec 2023

release

  • Claude Cowork Sync and Async interception capabilities for prompts and tool calls Guardrails for Claude Cowork, Sync and Async · Jul 2026 · source · release history
  • Custom Auth Headers added to Bring Your Own AI Agent setup under Argus Connectors Skill Governance Across Every AI Agent · May 2026 · source · release history
  • postman collection upload local command to run Postman collection uploads locally v1.40.5 · Jun 2024 · source · release history
  • Added basic auth in postman import v1.35.14 · Feb 2024 · source · release history
  • Added support to save HAR and Postman files when uploading traffic v1.32.6 · Dec 2023 · source · release history

example

  • Export captured API traffic for import into other tools like Postman or HAR viewers In the Akto UI, upload your traffic capture file; ensure the 'Save HAR' and 'Save Postman' options are selected during the upload process to generate the respective files. v1.32.6 · Dec 2023 · source
Traffic Interception and Proxy Support shipped Captures AI agent traffic via proxy or direct interception (including Claude/Async) to surface insights and enforce policies. 4 releases · 2 other sources · first seen Mar 2023

release

  • Claude Cowork Sync and Async interception capabilities for prompts and tool calls Guardrails for Claude Cowork, Sync and Async · Jul 2026 · source · release history
  • Domain-Based Proxy Routing routes AI domains through proxy while chatty domains bypass it Skill Governance Across Every AI Agent · May 2026 · source · release history
  • OpenCode Hook intercepts prompts and tool request/response traffic Skill Governance Across Every AI Agent · May 2026 · source · release history
  • Adds File and URL Guardrails to validate uploaded files and external URLs (audio, video, images, documents). Guardrails for Every AI Coding Workflows · Apr 2026 · source · release history

example

  • Enforce gateway-level PII scanning on every inbound prompt and outbound response routed through a LiteLLM proxy, without requiring each application team to implement their own checks. guardrails: - guardrail_name: "akto-validate" litellm_params: guardrail: akto mode: pre_call akto_base_url: os.environ/AKTO_GUARDRAIL_API_BASE akto_api_key: os.environ/AKTO_API_KEY default_on: true -… announced · seen Oct 2026 · source
  • Use the Burp extension to intercept and test gRPC or GraphQL traffic directly from your browser proxy. Install the Akto Burp Extension and ensure 'grpc' and 'graphql' are enabled in the extension settings. v1.28.5 · Mar 2023 · source
Custom Test Library Support shipped Allows users to define and import custom libraries to extend the capabilities of API security tests. 5 releases · first seen Oct 2023

release

  • Adds discovery support for locally hosted models on SGLang, vLLM, Docker Model Runner, and Ollama. Guardrails for Every AI Coding Workflows · Apr 2026 · source · release history
  • Select probe engine and modify hosts in the editor playground when validating agentic scans. Complete Observability Into your AI Agents · Feb 2026 · source · release history
  • View actual probe requests sent during scans for debugging visibility. Complete Observability Into your AI Agents · Feb 2026 · source · release history
  • Adds support for custom test libraries to extend scanning capabilities v1.32.8 · Jan 2024 · source · release history
  • Fetches tests from the tests-library repository instead of bundling them in the codebase v1.31.5 · Oct 2023 · source · release history
Identity and Access Management shipped Manages user authentication, roles, and permissions via native controls or integration with identity providers like Okta for SSO. 5 releases · first seen Jan 2024

Also counts toward: Role-based access control, Single sign-on

release

  • Get a high-level summary of top Agents and MCPs through Agentic Inventory Insights. Complete Observability Into your AI Agents · Feb 2026 · source · release history
  • Hugging Face Integration protects agents and models hosted or deployed via Hugging Face. Turning the Lights on for OpenClaw 💡 · Jan 2026 · source · release history
  • DevRev Integration fetches can be filtered by part type to restrict results to specific DevRev parts via Akto Argus. Turning the Lights on for OpenClaw 💡 · Jan 2026 · source · release history
  • jwt authentication bypass via kid param injection test now available in the test editor. v1.34.10 · Jan 2024 · source · release history
  • jwt authentication bypass via jwk header injection test now available in the test editor. v1.34.10 · Jan 2024 · source · release history
Agent Inventory Management shipped Discovers, maps, and manages AI agents, MCP servers, and skills across endpoints, cloud providers, and developer environments with registry controls. 3 releases · first seen Apr 2026

release

  • Copilot Studio Bot Filtering allows filtering by Bot ID under Argus Connectors Skill Governance Across Every AI Agent · May 2026 · source · release history
  • Adds SentinelOne Connector to discover and monitor SentinelOne managed endpoints for real-time guardrails. Guardrails for Every AI Coding Workflows · Apr 2026 · source · release history
  • Adds MCP Registry Control to allowlist approved MCP servers by importing registries via CSV URL. Guardrails for Every AI Coding Workflows · Apr 2026 · source · release history
AI-Assisted Analysis (AktoGPT) shipped Integrates generative AI to assist in the analysis of API security test results and configuration. 3 releases · first seen Apr 2023

Also counts toward: Built-in AI assistant, Ticketing integration

release

  • AI-generated summaries and insights are now included in scan results for identified findings Full AI Security Posture for Endpoints in Akto Atlas · Mar 2026 · source · release history
  • Jira Data Center integration supports expanded two-way sync, severity mapping, and custom field enrichment for agentic tickets. Turning the Lights on for OpenClaw 💡 · Jan 2026 · source · release history
  • Adds ChatGPT integration to provide AI-assisted analysis within the Akto interface v1.28.6 · Apr 2023 · source · release history
Observability and Red Teaming shipped Provides LLM observability with conversation insights, traces for agent traffic, and red teaming evaluations including malicious skill alerts. 2 releases · first seen May 2026

release

  • Introduces the Traces dashboard for LLM observability with Conversation Insights to automatically classify session topics. Trace Every Prompt, Tool Call, and Response · Jun 2026 · source · release history
  • Snowflake Agent Tracing captures traces, spans, and service graphs for agent traffic Skill Governance Across Every AI Agent · May 2026 · source · release history
Extended Compliance Mapping shipped Maps guardrail and API security activities to regulatory frameworks including EU AI Act, OWASP Agentic Top 10, NIST AI RMF, and Mitre ATLAS. 1 release · first seen Apr 2026

release

  • Adds Extended Compliance Mapping for EU AI Act, OWASP Agentic Top 10, NIST AI RMF, and Mitre ATLAS. Guardrails for Every AI Coding Workflows · Apr 2026 · source · release history
Agent LLM Provider Configuration shipped Allows configuration of AI agent backends with various large language model providers, including support for Databricks. 1 release · first seen Mar 2026

release

  • Databricks is supported as an LLM provider in agent configuration Full AI Security Posture for Endpoints in Akto Atlas · Mar 2026 · source · release history

Lines in monospace are the tool's own words: help text parsed from its source, or an endpoint from its API document. Under release, a line is our summary of a dated release. Under docs, it is quoted from the tool's own documentation or website. Each links back to the source it came from.

Score card

  1. Shipping velocity releases a month, last 12 months
  2. Documentation quality release-notes rubric, 0–100
  3. Breaking-change discipline how rarely a release breaks users, and notice given
  4. Maintenance risk quiet time against its own cadence, maintainers
  5. Innovation & surface new capabilities, API and MCP surface
  6. Community health
  7. Contributor trend distinct committers, this year against last
  8. Maintainer concentration bus factor now against a year ago
  9. Issue backlog trend issues closed per issue opened, 12 months
  10. Responsiveness median time to a maintainer’s first reply

Nine scores for Akto, each built from the releases, notes and API history this site tracks — and, on Researcher and Business, where it stands among every measured tool in its category and how that has moved.

Score cards are part of every paid plan.

See plans →

Each score is 0–100 on a published rubric, derived from data this site already shows. A dimension we cannot measure says so — it is never scored 0 and never enters a rank.

How this is scored
  • Shipping velocity — releases a month over the last 12 months, on a log scale where 16 a month scores 100. Needs 3 releases in the window.
  • Documentation quality — the release-notes rubric published on the analytics page, unchanged.
  • Breaking-change discipline — the share of releases carrying a breaking change (none scores 100, half or more scores 0). Only projects that label breaking changes are measured: a clean record cannot be told from an unlabelled one.
  • Maintenance risk — quiet time measured against the tool's own release cadence (quiet longer than 90 days and three typical gaps scores 0), plus the number of active maintainers and whether contributors are growing, where known. Higher is lower risk.
  • Innovation & surface — new capabilities in the feature ledger this year, API and MCP operations added, and the share of commits that are features: the mean of whichever we hold.
  • Community health (open-source tools only) — each is a direction, not a size: contributors this year against last, the bus factor now against a year ago, and issues closed per issue opened, where steady scores 50, doubled 100 and halved 0; plus the median time to a maintainer's first reply (an hour scores about 100, a month or more 0). A commercial card has no repository and carries none of the four.
  • Documented delivery (commercial tools) — when a vendor's documented new capabilities have slowed against its own baseline, that counts against the overall standing as heavily as two low dimensions. Steady delivery, or too little history to judge, leaves the standing alone; it is never a sixth score.
  • Open-source tools are scored on repository signals; commercial tools on their published changelog. Ranks compare tools within one category and one profile and need at least five measured peers; the overall standing needs three ranked dimensions. Best-in-breed or consolidator is a shape, not a quality, and is never scored.

Release-note detail over time

See how much detail Akto puts in its release notes, quarter by quarter, and compare it with tracked tools in the same category. This history uses up to ten retained, reviewed notes per tool; sparse or blank older quarters may reflect that limit.

Checking release-note history…

Explore the full chart →

Website history

akto.io, every change

Akto's home, pricing and product pages and 23 more pages as they looked each month from November 2021 to October 2026: 40 renders, 8 changes of tagline or palette. Step through them, play them, or put any two months side by side.

Website history is included with Researcher and Business.

See plans →

Coverage

Missing something? Tell us

What Akto connects to, runs on and detects, read from its release notes and docs. So far: 1 new integration, 1 new detection.

Show

2 changes, tracked since Oct 22, 2026.

  • Seen Oct 222026

    new Akto as native LiteLLM guardrail provider

    Akto is a native guardrail provider in LiteLLM, confirmed directly in LiteLLM's own documentation and announced on LiteLLM's official blog.

    Source ↗

  • Seen Oct 222026

    new Model-based semantic PII detection for contextual and paraphrased PII

    With LiteLLM, akto

    Model-based detection evaluates meaning rather than shape, catching PII that's paraphrased, spelled out, split across a sentence, or described rather than stated directly in a recognizable format.

    Source ↗

How we count

Read from 1 of 83 release notes and docs updates we hold for Akto. "First seen" is the earliest note that names something; "last" is the latest. Our history may start partway through Akto's life, so an old integration can show a recent first-seen date.

Each change counts once: "added 40 checks" is one line, so the numbers measure how often coverage moves, not how big the catalogue is or how well it detects.

Releases

Coverage in all entries

83 entries

  1. October 20261
  2. August 20261
  3. July 20261
  4. June 20261
  5. May 20261
  6. April 20261
  7. March 20261
  8. February 20261
  9. January 20261
  10. February 20251
  11. January 20254
  12. July 20241
  13. June 20243
  14. May 202410
  15. April 20247
  16. March 20245
  17. February 20249
  18. January 202411
  19. December 20234
  20. November 20232
  21. October 20234
  22. September 20234
  23. August 20232
  24. June 20233
  25. May 20231
  26. April 20231
  27. March 20232
    Coverage in all entries

    83 entries

    Project health

    Issue, contributor and maintainer activity in akto-api-security/akto, 2023-10 – 2026-09, as of 2026-09-25. Twelve-month figures first; the trend lines run the whole window.

    1. Contributors not measured distinct committers, last 12 months
    2. Maintainers not measured core set, last 12 months
    3. Bus factor not measured committers behind half the commits
    4. Community-filed not measured of issues opened, last 12 months
    5. Median time to close not measured issues closed, last 12 months
    6. Open backlog not measured open issues today
    1. Issues opened / month not measured
    2. Open backlog not measured
    3. Contributors / month not measured
    4. Commits / month not measured
    5. Stars not measured
    Issue themes, last 12 months not measured

    Counts from the project's public repository and git history; no individuals are identified. Maintainers are the committers covering 80% of the last year's commits. how we measure this

    Add the badge to your README

    Maintain this project? The badge links readers straight to this page, so they can follow every release here.

    Tracked by Cyber Toolchain Choose a badge style and copy the code →
    browse all tools → score card for your toolchain →