AgentOS
by AgentOS · Open-source TypeScript runtime for autonomous AI agents
BenchRank score
Screenshots of AgentOS
Homepage
Overview
AgentOS is an open-source TypeScript runtime for building autonomous AI agents, installed via npm and self-hosted. It provides multi-agent orchestration, cognitive memory using Ebbinghaus decay and reconsolidation, multimodal RAG, guardrails, voice pipelines and 11 LLM providers. Agents can write their own TypeScript functions mid-task and spawn specialists, subject to an LLM judge.
- Best for
- TypeScript teams self-hosting autonomous multi-agent systems that need long-term memory
- Pricing
- No prices are shown; the core is Apache 2.0 licensed with MIT agents, extensions and guardrails, installed from npm and run on your own infrastructure.
- Runs on
- Self-hostedCLI
Strengths and trade-offs
Strengths
- Apache 2.0 core, MIT agents and extensions, self-hosted
- One TypeScript runtime covering 11 LLM providers
- 85.6% on LongMemEval-S, 0.4 below closed-source Emergence.ai
- Agents forge tools and spawn specialists at runtime
Trade-offs
- Runtime-generated tools are approved by an LLM judge, not a person
- Workbench desktop app is listed as download coming soon
- TypeScript only; no other language SDK is mentioned
- 610 stars and 91 forks point to a small ecosystem
How AgentOS markets itself
A structured read of the promise, proof and page design on AgentOS’s captured homepage.
Homepage capture
“Emergent intelligence for adaptive agents”
- Angle: AI-native
- Hero: Abstract graphic
Pricing
Published plans and prices from AgentOS’s own pricing page.
How this score is made up
Each dimension is scored out of 100 and combined into the headline score using fixed weights.
MCP support
Whether an agent can drive the product through the Model Context Protocol, and how much setup that takes.
API quality
Public API surface: machine-readable spec, official SDKs, documented auth, errors, rate limits and versioning.
Documentation
Publicly reachable docs — coverage, freshness, code samples and machine readability.
Agent friendliness
How readable the site is to an automated client: llms.txt, structured data, server-rendered content, crawler access.
Changelog
A public, dated record of what shipped and when — the clearest signal that a product is still alive.
Marketing site structure
Whether the site answers a buyer's questions: clear positioning, the pages that matter, and accessibility.
Page speed
How fast the site loads for real visitors: Chrome UX Report 75th-percentile LCP, INP and CLS, with a Lighthouse mobile run standing in where a site has too little traffic for field data.
Operational trust
Status page and incident history, security disclosure, compliance and data-processing documentation.
Measured, but not part of the score
Useful to know, but not a mark for or against the product — so these do not affect the ranking.
Openness
Source availability, self-hosting, data export and open standards. Scored and shown, but not part of the composite — paid SaaS is not worse for being paid SaaS.
Maintenance
Release cadence and repository activity. Scored and shown, but not part of the composite — it is only measurable for open repositories.
This doesn’t look right — report a problem with AgentOS’s score
Where this comes from
The AgentOS pages BenchRank reads when it scores the product — its documentation, release notes, status and security pages, and its repository where there is one.
Alternatives in AI Development Platforms
Ranked 1
85.5 — BenchRank score out of 100Mem0
Mem0 · Hosted memory layer for AI agents, with Python and Node SDKs
Best for: Developer teams adding persistent memory to AI agents through a hosted API, with a free tier
Ranked 2
83.7 — BenchRank score out of 100Nango
Nango · Code-first integration platform covering 900+ APIs
Best for: Product teams building many third-party API integrations into a SaaS product or AI agent
Ranked 3
81.4 — BenchRank score out of 100Supermemory
Supermemory · Memory and retrieval layer for AI agents
Best for: Developers giving AI agents persistent memory and retrieval through a single hosted API.
Is this your product?
Claim AgentOS to manage its profile. Claiming lets you suggest edits to the descriptive fields — it never changes scores or rankings.