The section your link pointed to isn't on Superagent's page any more, so we've brought you to the top.
Superagent is an open-source SDK for AI agent safety that blocks prompt injections, redacts PIIPIIPersonally Identifiable Information — data that can identify a specific individual, such as names, email addresses, or SSNs. Cyber tools flag or redact it to limit exposure and meet privacy regulations. and secrets, and scans repositories for threats.
Superagent is an open-source SDK, released under MIT, that adds safety checks to AI agents at runtime, blocking prompt injections and unsafe tool calls, redacting PII, PHIPHIProtected Health Information: individually identifiable health data regulated under the US HIPAA law, whose strict handling requirements drive cyber tools to audit, mask, or restrict access to it., and secrets from text, and scanning repositories for agent-targeted attacks like repo poisoning. It ships as TypeScript and Python client libraries that call out to a guard/redact/scan service, so teams wire it directly into an agent's request path rather than deploying it as a standalone appliance. It is built for developers building or hardening AI agents rather than for traditional SOCSOCA security operations center, the team or function that monitors threats, investigates alerts and coordinates incident response. Its work can be internal, outsourced or shared. or network security staff, sitting in the emerging ai-security category alongside runtime protection and data-leak-prevention tools. First committed in 2023 and backed by Y Combinator, it has drawn 86 contributors and 241 commits in the past year, indicating active development.
Superagent is an open-source SDK for AI agent safety that blocks prompt injections, redacts PII and secrets, and scans repositories for threats.
Which incoming messages to my agent are prompt injections trying to hijack its behavior?
classifies the input at runtime and returns a block or allow verdict along with the specific violation types it detected, before the message reaches the agent's tool-calling logic
Is my agent about to leak sensitive data in its response?
scans outgoing text for PII, PHI, and secrets such as emails and SSNs and returns the same text with each one swapped for a labeled redaction tag
Which tool calls my agent is about to make are unsafe rather than just unexpected?
runs the proposed call through the same guard check as user input and returns a block verdict with the violation type when it looks like an unsafe action rather than normal tool use
Does this repository someone wants me to pull in contain instructions planted to hijack my agent?
scans the repository's contents for known agent-targeted attack patterns like repo poisoning and returns a security report naming what it found
Which specific rule or category caused a message to get blocked?
returns the violation types alongside the block verdict, so the reason is named rather than left as a bare pass or fail
Built from Superagent'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.
+Firewall Service ManagementshippedProvides CLI, container, and package-manager based deployment, configuration, and execution controls for the ai-firewall cyber toolchain component.13 releases · 9 other sources · first seen Aug 2025▸
Also counts toward: Command-line interface
release
13 total
Adds GitHub Packages registry support via @superagent-ai/ai-firewall npm package
node-v0.0.8 · Sep 2025
· source
· release history
Adds the ai-firewall start --port <number> --config <path> CLI interface for configuring port and config file
node-v0.0.8 · Sep 2025
· source
· release history
Enables Docker image access at ghcr.io/superagent-ai/superagent/node:0.0.6
node-v0.0.6 · Sep 2025
· source
· release history
Enables installation via npm install -g ai-firewall or GitHub Packages @superagent-ai/ai-firewall
node-v0.0.6 · Sep 2025
· source
· release history
Adds ai-firewall CLI subcommand to launch the firewall service
node-v0.0.6 · Sep 2025
· source
· release history
Adds --port argument to set the listening port (e.g. 8080)
node-v0.0.6 · Sep 2025
· source
· release history
example
9 total
Start the ai-firewall service on a specific port using a custom config file.$ ai-firewall start --port 8080 --config superagent.yaml
node-v0.0.8 · Sep 2025
· source
Start the firewall service on port 8080 using a custom configuration file.$ ai-firewall start --port 8080 --config superagent.yaml
node-v0.0.6 · Sep 2025
· source
Pull the specific node version of the superagent tool from the container registry.$ docker pull ghcr.io/superagent-ai/superagent/node:0.0.6
node-v0.0.6 · Sep 2025
· source
Install the firewall tool globally via npm to make the ai-firewall command available.$ npm install -g ai-firewall
node-v0.0.6 · Sep 2025
· source
Start the firewall service using a custom YAML configuration file$ ai-firewall start --port 8080 --config vibekit.yaml
node-v0.0.4 · Aug 2025
· source
Install the tool globally via npm for immediate CLI access$ npm install -g ai-firewall
node-v0.0.4 · Aug 2025
· source
+LLM Provider SupportshippedSupports multiple Large Language Model providers including Anthropic, Cohere, Azure OpenAI, Hugging Face Hub, and Claude 2.18 releases · 1 other source · first seen May 2023▸
release
18 total
Adds GPT-4o support for LLM interactions.
v0.2.39 · May 2024
· source
· release history
Adds Groq integration for LLM provider support
v0.2.32 · Apr 2024
· source
· release history
Adds Mistral integration for LLM provider support
v0.2.32 · Apr 2024
· source
· release history
Adds Amazon Bedrock as a supported LLM provider for agents
v0.2.29 · Apr 2024
· source
· release history
saml.llm_params setting allows passing LLM-specific parameters (such as temperature, top_p, etc.) during SAML authentication flows
v0.2.21 · Mar 2024
· source
· release history
example
Configure Superagent to use an Azure OpenAI deployment instead of a standard provider via the UI settings.$ In the Superagent UI, navigate to Settings > Providers and select 'Azure OpenAI' as the active model provider.
v0.1.52 · Jan 2024
· source
+Superagent ToolsshippedEnables superagents to use external tools such as Wolfram Alpha and Replicate-hosted models.14 releases · 3 other sources · first seen Jun 2023▸
Adds the scrapingbee tool to the agent's available actions
v0.2.23 · Mar 2024
· source
· release history
Adds the new HAND_OFF tool type to enable routing conversations to a human operator through intermediate steps
v0.1.31 · Nov 2023
· source
· release history
Add possibility to fetch URLs on runtime allowing dynamic HTTP requests during execution
v0.1.6 · Sep 2023
· source
· release history
Add support for a web crawler enabling agents to browse the web directly
v0.1.6 · Sep 2023
· source
· release history
example
Create and attach the new HAND_OFF tool to an existing agent using the SDK.$ const {data: tool} = await superagent.tool.create({ type: "HAND_OFF", name: "Human hand-off", description: "Useful for handing off the conversation to a human operator" }); await…
v0.1.31 · Nov 2023
· source
Adjust caching behavior through the interface without editing config files.$ In the Superagent web UI, locate the `cache` setting and configure your desired values.
v0.0.60 · Sep 2023
· source
Enable a Superagent to perform complex mathematical computations by attaching the Wolfram Alpha integration.$ In the console, go to your Agent configuration and add the 'Wolfram Alpha' tool.
v.0.0.15 · Jun 2023
· source
+Document IngestionshippedSupports ingesting various document types including URLs, YouTube videos, Markdown, and updating existing documents.15 releases · 1 other source · first seen May 2023▸
Also counts toward: REST API
release
15 total
Re-introduces loading YouTube videos as a data source for AI Assistants
v0.1.20 · Oct 2023
· source
· release history
Reintroduce local_file_uploads feature allowing users to upload files directly via the interface
v0.1.8 · Sep 2023
· source
· release history
Adds github loader as a new data source integration
v0.1.0 · Sep 2023
· source
· release history
example
Load all content from a public GitHub repository into an Agent for RAG without configuring external URLs.$ In the UI, create a new Data Source and select 'GitHub Repository', then enter the repo URL.
v0.0.41 · Aug 2023
· source
+Agent UIshippedProvides a visual interface for testing, running, building agents visually, and managing them with tags.12 releases · 2 other sources · first seen Jun 2023▸
release
12 total
stop button added to the Chat UI to manually interrupt an active streaming response
v0.1.39 · Dec 2023
· source
· release history
Adds the ability to copy individual chat messages in the Superagent interface.
v0.1.32 · Nov 2023
· source
· release history
Add initial_message to agent configuration to set a custom intro message for the chatbot
v0.1.18 · Oct 2023
· source
· release history
Enables markdown table rendering in agent responses or configurations
v0.1.4 · Sep 2023
· source
· release history
Adds a copy ID button to the agent detail page for easy copying of the agent identifier
v0.1.4 · Sep 2023
· source
· release history
Stop a long-running or stuck response generation in the Chat UI without refreshing the page.$ Click the `stop` button located in the Chat UI while a stream is active
v0.1.39 · Dec 2023
· source
When copying a specific AI or user response from a conversation for reference or external use.$ In the Superagent UI, locate the desired chat message and click the copy icon/button associated with it.
v0.1.32 · Nov 2023
· source
+Vector Store IntegrationshippedAllows configuring different vector database backends for agent storage and retrieval.8 releases · 1 other source · first seen Aug 2023▸
release
8 total
Adds SuperRag support in the Agents UI page, allowing users to connect agent instances to vector stores for retrieval-augmented generation.
v0.2.15 · Mar 2024
· source
· release history
Create an agent that retrieves information from your knowledge base during conversation.$ In the Superagent Agents page, select 'Create Agent', then enable SuperRag and configure your vector store connection.
v0.2.15 · Mar 2024
· source
+DeploymentshippedSupports local setup via bash scripts, Dockerfiles, docker-compose, and deployment to Replit.8 releases · first seen May 2023▸
release
8 total
Adds Docker image ghcr.io/superagent-ai/superagent/node:0.0.8 for containerized deployment
node-v0.0.8 · Sep 2025
· source
· release history
Add configuration changes for deploying Superagent to Replit
v0.1.7 · Sep 2023
· source
· release history
First-class support for deploying to the Replit Autoscale platform
v0.1.3 · Sep 2023
· source
· release history
helm charts added to the repository for declarative installation.
v0.0.57 · Aug 2023
· source
· release history
Adds a docker-compose.yml file to enable one-command local setup of Superagent
v0.0.38 · Jul 2023
· source
· release history
+Agent TracingshippedSaves logs of agent traces and decision-making processes for debugging.5 releases · 1 other source · first seen Jun 2023▸
release
Add Langfuse sdk_integration arg to configure Langfuse integration programmatically
v0.2.17 · Mar 2024
· source
· release history
Adds Langfuse host url configuration option in the UI to connect to self-hosted Langfuse instances
v0.1.38 · Dec 2023
· source
· release history
Adds Langfuse integration as a drop-in replacement for Langsmith
v0.1.28 · Nov 2023
· source
· release history
Adds LangSmith integration for request/response tracing
v0.0.55 · Aug 2023
· source
· release history
Adds Agent logs to save traces and decision-making for debugging and enhancement
v.0.0.16 · Jun 2023
· source
· release history
example
Connect Superagent to your on-premise Langfuse instance for audit logging.$ In the UI Settings, enter your Langfuse host URL in the newly added 'Langfuse host url' field.
v0.1.38 · Dec 2023
· source
+Search AgentshippedProvides a specialized agent capable of keyword-based and pattern-based search queries with tunable prompts.4 releases · 1 other source · first seen Jun 2023▸
Supports both keyword-based and pattern-based search queries within the new Search Agent
v.0.0.13 · Jun 2023
· source
· release history
Allows tunning the Search Agent via a prompt parameter for specific instructions
v.0.0.13 · Jun 2023
· source
· release history
Adds a new Search Agent capability that uses advanced search techniques to find and retrieve data based on specific criteria
v.0.0.13 · Jun 2023
· source
· release history
example
Configure an agent to perform pattern-based search queries.$ { "type": "search", "query_type": "pattern", "prompt": "Find all emails matching domain @example.com" }
v.0.0.13 · Jun 2023
· source
+Agent PromptsshippedAllows creating, listing, and updating prompts associated with agents.5 releases · first seen May 2023▸
release
Exposes prompting interface to the DocumentAgent
v.0.0.18 · Jun 2023
· source
· release history
Adds functionality for patching prompts via the core library
v.0.0.14 · Jun 2023
· source
· release history
Add possibility to attach custom prompts to an agent
v.0.0.10 · May 2023
· source
· release history
Adds capability to attach a prompt to an Agent
v.0.0.9 · May 2023
· source
· release history
Adds API endpoints for creating, listing, and destroying prompts
v.0.0.9 · May 2023
· source
· release history
+Agent Response StreamingshippedAllows real-time streaming of agent outputs via API and CLI interfaces.3 releases · 1 other source · first seen Dec 2023▸
Also counts toward: Command-line interface
release
Adds a switch for enabling or disabling streaming output
v0.2.14 · Mar 2024
· source
· release history
Adds --stream flag to superagent invoke CLI subcommand to enable streaming responses from invoked agents
v0.1.63 · Jan 2024
· source
· release history
The workflow invoke endpoint supports streaming responses
v0.1.44 · Dec 2023
· source
· release history
example
Stream the output of an agent invocation in real time via the CLI.$ superagent invoke --agent-id <agent_id> --prompt "<query>" --stream
v0.1.63 · Jan 2024
· source
+Enterprise AuthenticationshippedEnables Single Sign-On (SSO) and enterprise identity provider integration for the service interface.3 releases · 1 other source · first seen Jul 2023▸
Shared capability: Single sign-on
Also counts toward: Single sign-on
release
Add LLM Agent to SAML enables SAML-based authentication for LLM Agents
v0.2.7 · Feb 2024
· source
· release history
Add indentify tracking to everyone who signs in
v0.2.1 · Feb 2024
· source
· release history
SSO support is now available for UI login via the Support SSO PR.
v0.0.39 · Jul 2023
· source
· release history
example
Enable enterprise identity provider integration for the Superagent service interface.$ In the UI configuration settings, enable SSO.
v0.0.39 · Jul 2023
· source
+Agent ManagementshippedAllows creating, reading, and deleting Agents via REST endpoints.4 releases · first seen May 2023▸
Also counts toward: REST API
release
Adds Pagination for workflows and agents page
v0.1.49 · Dec 2023
· source
· release history
GET /agents and GET /workflows now support pagination parameters
v0.1.44 · Dec 2023
· source
· release history
Enables agents to execute ChatGPT plugins as tools
v0.0.40 · Aug 2023
· source
· release history
+API InterfaceshippedStandardizes request structures and input payloads for the API.4 releases · first seen Jun 2023▸
release
Adds v1 and v0 version prefixes for API routing
v0.1.0 · Sep 2023
· source
· release history
Adds support for defining response models in the API schema
v0.1.0 · Sep 2023
· source
· release history
Adds support for passing in JSON inputs
v0.0.28 · Jul 2023
· source
· release history
Introduces unified input payload for the API, standardizing how requests are structured
v.0.0.21 · Jun 2023
· source
· release history
+Workflow Tracing and ObservabilityshippedEnables tracking agent execution traces via Langfuse integration and analytics data for improved observability.3 releases · first seen Dec 2023▸
release
Add Langfuse sdk_integration arg to configure Langfuse integration programmatically
v0.2.17 · Mar 2024
· source
· release history
Adds the ability to fetch usage and tracing statistics from Langfuse
v0.1.56 · Jan 2024
· source
· release history
Adds Langfuse host url configuration option in the UI to connect to self-hosted Langfuse instances
v0.1.38 · Dec 2023
· source
· release history
+Nested AgentsshippedAllows an agent to invoke and run another agent as a tool.2 releases · 1 other source · first seen Jul 2023▸
release
Passes session_id between nested agents to maintain conversation context across agent hierarchies
v0.1.38 · Dec 2023
· source
· release history
Introduces Agent-as-a-Tool to allow an Agent to run another Agent (Nested Agents)
v0.0.30 · Jul 2023
· source
· release history
example
Use the new Agent-as-a-Tool feature to enable nested agent execution.$ N/A - Tooling feature
v0.0.30 · Jul 2023
· source
+Code InterpretershippedEnables agents to execute code in a sandboxed environment for file analysis, computation, and chart generation.3 releases · first seen Sep 2023▸
Also counts toward: Python scripting support
release
Enables creating charts and performing computations via the new code interpreter API
v0.1.14 · Oct 2023
· source
· release history
Adds the e2b code execution tool integration for running code in a sandboxed environment
v0.1.14 · Oct 2023
· source
· release history
Alpha release of the code interpreter API for file analysis and compute/calculations
v0.1.3 · Sep 2023
· source
· release history
+API AuthenticationshippedSupports authenticating API requests using API tokens or Bearer tokens.3 releases · first seen May 2023▸
release
Adds Bearer token support for authenticating requests to the agent predict interface.
v0.0.33 · Jul 2023
· source
· release history
Add possibility to access API using API tokens
v.0.0.11 · May 2023
· source
· release history
Introduces the ApiToken model to authenticate requests against Agent endpoints
v.0.0.1 · May 2023
· source
· release history
+Output Schema ControlshippedAllows configuring agents to output structured data formats such as JSON via schema definitions.1 release · 1 other source · first seen Mar 2024▸
Also counts toward: JSON data export
release
Setting Output Schema for LLM agent type
v0.2.24 · Mar 2024
· source
· release history
example
Configure the agent to output structured JSON data using the new Output Schema setting.$ config { "type": "llm", "output_schema": { "type": "object", "properties": { "result": { "type": "string" } } } }
v0.2.24 · Mar 2024
· source
+Real-Time IntegrationsshippedBrings real-time data into agents via Psychic integration.2 releases · first seen Jul 2023▸
release
Subscription events sent to Loops integration
v0.2.2 · Feb 2024
· source
· release history
Adds Psychic integration to bring real-time data from APIs into Agents
v0.0.28 · Jul 2023
· source
· release history
+LLM Segment TrackingshippedCaptures LLM model information and request status codes during agent execution for detailed debugging.2 releases · first seen Jan 2024▸
release
Adds LLM model information to the segment tracker
v0.1.59 · Jan 2024
· source
· release history
Adds analytics tracking data to agent responses for improved observability
v0.1.58 · Jan 2024
· source
· release history
+User ProfilesshippedSaves metadata for user profiles at the time of signup.2 releases · first seen May 2023▸
release
Adds email field to the ApiUser API response model for user identity details
v0.1.8 · Sep 2023
· source
· release history
+Session ManagementshippedAllows creating separate sessions when invoking agents.2 releases · first seen Aug 2023▸
release
Adds ability to create sessions in the shareable chat UI
v0.0.51 · Aug 2023
· source
· release history
Adds the ability to create separate sessions when invoking agents
v0.0.40 · Aug 2023
· source
· release history
+Agent SharingshippedAllows agents to be marked as public and shared externally.2 releases · first seen Jul 2023▸
release
Adds a new Agent model with support for public listing and cloning capabilities
v0.0.46 · Aug 2023
· source
· release history
Adds public status to agents, enabling them to be shared externally.
v0.0.31 · Jul 2023
· source
· release history
+OpenAPI IntegrationsshippedConnects agents to third-party APIs using the OpenAPI toolkit.1 release · 1 other source · first seen Jul 2023▸
release
Adds OpenAPI toolkit support to connect an Agent to any third-party API
v0.0.30 · Jul 2023
· source
· release history
example
Connect your assistant to external APIs using the new OpenAPI toolkit.$ N/A - Tooling feature
v0.0.30 · Jul 2023
· source
+Zapier IntegrationsshippedEnables building AI assistants that interact with Zapier workflows.1 release · 1 other source · first seen Jul 2023▸
release
Adds Zapier toolkit support for building AI assistants via Zapier
v0.0.30 · Jul 2023
· source
· release history
example
Build AI assistants that interact with Zapier workflows.$ N/A - Tooling feature
v0.0.30 · Jul 2023
· source
+CSV AnalysisshippedAllows questioning the contents of uploaded CSV files.1 release · 1 other source · first seen Jul 2023▸
release
Adds support for Q&A over CSV files to your Agents
v0.0.29 · Jul 2023
· source
· release history
example
Enable CSV analysis for an Agent to allow questioning its contents.$ Upload a .csv file directly into the Agent interface
v0.0.29 · Jul 2023
· source
+Document SummarizationshippedAutomatically generates summaries when documents are added to an agent and allows reviewing them.1 release · 1 other source · first seen Jul 2023▸
release
Adds summary tool whenever a document is added to an Agent
v0.0.29 · Jul 2023
· source
· release history
example
Review the auto-generated summary of newly uploaded documents.$ Check the Agent's document view after adding a new file to see the automated summary
v0.0.29 · Jul 2023
· source
+Agent RuntimeshippedProvides the core functionality to invoke and execute agents.2 releases · first seen May 2023▸
release
Adds the ability to execute a ConversationalRetrievalChain workflow.
v.0.0.4 · May 2023
· source
· release history
Agent invocation functionality (core agent runtime)
v.0.0.2 · May 2023
· source
· release history
+Telemetry and Usage TrackingshippedProvides built-in support for tracking usage metrics and telemetry data.1 release · first seen Aug 2025▸
release
Adds telemetry support for tracking usage metrics.
node-v0.0.2 · Aug 2025
· source
· release history
+Agent Memory SharingshippedEnables the transfer of memory state between steps or agents within a workflow.1 release · first seen Mar 2024▸
release
Workflows can now pass memory between steps or agents
v0.2.18 · Mar 2024
· source
· release history
+Research Tool IntegrationshippedAdds support for a research tool powered by Tavily to enhance information gathering capabilities.1 release · first seen Mar 2024▸
release
Add support for research tool powered by Tavily
v0.2.19 · Mar 2024
· source
· release history
+OpenAI Assistants SupportshippedAdds compatibility with OpenAI's native Assistants API for agent execution.1 release · first seen Feb 2024▸
+DebuggingshippedProvides structured error logging in the agent runtime to enhance error visibility.1 release · first seen Jul 2023▸
release
Enhances error visibility with new structured error logging in the agent runtime
v0.0.38 · Jul 2023
· source
· release history
+Client SDKsshippedGenerates TypeScript SDKs for client-side integration.1 release · first seen Jul 2023▸
Also counts toward: Client SDKs
release
Adds a TypeScript SDK generator for client-side integration.
v0.0.31 · Jul 2023
· source
· release history
+Agent MigrationshippedMarks the old agentic infrastructure as deprecated, requiring recreation of agents for new functionality.1 release · first seen Jun 2023▸
release
The old Agentic infrastructure is deprecated; agents must be recreated to function in this version
v.0.0.21 · Jun 2023
· source
· release history
+Multi-Document AgentsshippedAllows a single agent to operate across multiple document sources.1 release · first seen Jun 2023▸
release
Enables multi-document capabilities allowing a single Agent to operate across multiple sources
v.0.0.21 · Jun 2023
· source
· release history
+Document ProcessingshippedEnables using multiple text splitters when ingesting documents.1 release · first seen Jun 2023▸
release
Enable multiple text splitters to be used via the API when ingesting documents
v.0.0.20 · Jun 2023
· source
· release history
+Agent State PersistenceshippedRetains agent state information in memory between invocations.1 release · first seen May 2023▸
release
Memory subsystem for agent state retention
v.0.0.2 · May 2023
· source
· release history
+AI Agent Safety SDKdocumentedProvides an open-source SDK to secure agents by blocking prompt injections, redacting PII, and scanning for threats.1 other source▸
docs
Open-source SDK for AI agent safety: blocks prompt injections, redacts PII/secrets, and scans repositories for agent-targeted threats.
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.
Command line
View
Source
No command matches.
load a captured run
composed command
No matchesTry a different search, or clear a filter to see more.
option surface across analysed releases
options at that releaseadded, per releaseremoved, per release
option
found in
since
description
No matchesTry a different search, or clear a filter to see more.
option changes per release — drag across the rail to set a range
→
Values are placeholders taken from each option’s declared default.
Nothing is executed here — the output shown is a recording of a run
that already happened.
Score card
Shipping velocityreleases a month, last 12 months
Documentation qualityrelease-notes rubric, 0–100
Breaking-change disciplinehow rarely a release breaks users, and notice given
Maintenance riskquiet time against its own cadence, maintainers
Innovation & surfacenew capabilities, API and MCP surface
Community health
Contributor trenddistinct committers, this year against last
Maintainer concentrationbus factor now against a year ago
Issue backlog trendissues closed per issue opened, 12 months
Responsivenessmedian time to a maintainer’s first reply
Nine scores for Superagent, 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.
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 Superagent 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.
Issue, contributor and maintainer activity in superagent-ai/superagent, 2023-10 – 2026-09,
as of 2026-09-25. Twelve-month figures first; the trend lines run
the whole window.
Contributors5+3 vs prior 12 months
Maintainers1+0 joined · −0 left, last 12 months
Bus factor1committers behind half the commits
Community-filed58%of issues opened, last 12 months
Median time to close6.9 daysfirst maintainer reply 6.9 days
Open backlog9of 436 issues ever filed
Issues opened / month1 · 0communitymaintainers
Open backlog9
Contributors / month0
Commits / month0
Stars6,748
Issue themes, last 12 months
bugs 7%
features 27%
other 66%
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.