Agent platform landscape
Solutions are clustered by archetype — managed platforms, agent frameworks, and infrastructure layers — and rated across 15 capability clusters. Filter the directory, pick up to 4 solutions, and compare them side by side with SOAT.
14 of 14 solutions
Baseline
Self-hosted infrastructure layer for production-ready AI agents: IAM, storage, knowledge, memory, orchestration, guardrails, and traces from one Node.js server backed by PostgreSQL.
AWS managed agent platform composed of modular services — Runtime, Harness, Memory, Gateway, Identity, Policy, Code Interpreter, Observability, and Evaluations — consumed as AWS APIs and usable independently or together. There is no self-hosted distribution.
Anthropic's agent stack on platform.claude.com: the Messages API and tool use, plus Managed Agents — versioned agent configs, per-session containers Anthropic provisions, an SSE event stream, MCP servers with vault-held credentials, skills, memory stores, and cron-scheduled deployments. Workspaces and the Admin API scope keys and resources; the control plane is Anthropic-operated, though tool execution can move to a self-hosted sandbox.
Python framework for orchestrating role-based autonomous agents, combining Crews (agent teams with task delegation) and Flows (event-driven, state-managed workflows). A separate commercial product, CrewAI AMP, adds managed deployment, a trace dashboard, and webhook automations.
Plugin-based open-source agent framework from DeepSeek AI ("everything is a plugin") built on the Cordis composable plugin system, with a web UI and CLI for building and running custom agents.
Open-source LLM application platform providing a visual workflow canvas, RAG knowledge bases, agent nodes, and a plugin marketplace, served by a self-hostable Docker Compose stack with PostgreSQL, Redis, Celery workers, a pluggable vector database, and a sandbox service. Applications publish as web apps, REST APIs, MCP servers, or reusable tools.
Open-source agent runtime from Nous Research with a built-in learning loop (skills from experience), agent-curated memory, 40+ tools plus MCP, and a multi-platform gateway (Telegram, Discord, Slack, WhatsApp, Signal, CLI).
One stack from one vendor, rated together: LangChain for standardized model interfaces and the largest third-party integration catalog, LangGraph for durable stateful agent graphs, the LangGraph Platform Agent Server for assistants, threads, runs, and cron, and the commercial LangSmith for tracing and evals. The libraries are MIT and run wherever you host them; tracing, evals, and the hosted server are paid products.
Open-source server for stateful LLM agents (formerly MemGPT) that persists agent state, memory blocks, and archival passages in PostgreSQL with pgvector, exposed over a REST API and SDKs. Deployable via Docker or usable as a hosted service, with agent state surviving context-window eviction.
Multi-language (.NET, Python, Go) library for building agents and graph-based multi-agent workflows, positioned as the successor to AutoGen and Semantic Kernel. Provides agents, sessions, context providers, middleware, MCP clients, OpenTelemetry instrumentation, and an evaluation framework, with optional Microsoft Foundry hosting.
Managed Azure service for building and scaling agents as either configuration-defined prompt agents or container-based hosted agents, with the Responses API as the single model and tool entry point. Runtime, tools, Entra identity, tracing, and evaluation live inside a Foundry project; there is no self-hosted distribution.
OpenAI's agent stack: the MIT-licensed Agents SDK (agent loop, sessions, handoffs, guardrails, tracing) plus the Responses API, OpenAI-hosted tools (web search, file search, code interpreter, hosted MCP), and a managed Traces dashboard. Execution and hosted tools depend on OpenAI's API; there is no self-hosted control plane.
Open-source personal AI assistant framework: a local gateway control plane connecting AI models to WhatsApp, Telegram, Slack, Discord, Signal, and iMessage, with tools, skills, MCP, scheduling, and optional sandboxed execution — built for a single operator who owns their data.
Google Cloud's managed platform for building and deploying agents: Agent Development Kit, managed Agent Engine runtime, RAG Engine, and Google Cloud IAM, billing, and observability.
| Capability cluster | SOAT |
|---|---|
| Agent runtimeAgent loop, sessions, and generation lifecycle. | Agents, sessions, chats, and generations with full lifecycle tracking.Source |
| OrchestrationMulti-step pipelines, workflows, and triggers. | DAG orchestrations, workflow state machines, durable tasks, and triggers (manual, webhook, schedule).Source |
| Knowledge & memoryDocuments, embeddings, semantic search, and recall. | Documents with per-chunk embeddings, named memories, unified semantic search, and ingestion rules for PDFs, images, and audio.Source |
| Tools & integrationTool calling, MCP, providers, and webhooks. | HTTP, MCP, client, and agent-to-agent tools; model routes with failover; webhooks; any LLM provider.Source |
| Identity & governanceIAM, guardrails, approvals, quotas, and audit. | AWS-inspired IAM, actors, scoped API keys, guardrails, human approvals, quotas, and an append-only audit log.Source |
| ObservabilityTraces, activity, usage, and failure queues. | Traces of every tool call and model response, activity feed, usage/cost tracking, and an exceptions queue.Source |
| Data & secretsFile storage and encrypted secrets. | File storage over local/S3/GCS backends and encrypted secrets storage.Source |
| EvaluationDatasets, scorers, and eval-gated improvement. | Datasets, scorers, and scored runs; eval-gated promotion of agent versions.Source |
| ChannelsBuilt-in gateways to messaging platforms and UIs. | Surfaces are REST, MCP, CLI, and SDK — no built-in gateways to messaging platforms like Slack, WhatsApp, or Telegram. |
| Code executionSandboxed code or terminal runtimes for agents. | Tool types are HTTP, MCP, client, and agent-to-agent — no built-in sandboxed code or terminal runtime. |
| Human-in-the-loopPausing a run for human approval, then resuming it. | Approvals are a first-class human-decision queue with frozen evidence, and guardrails classify each tool call so risky actions pause for a decision.Source |
| Multi-tenancyProjects or workspaces scoping resources and permissions. | Projects are multi-tenant namespaces scoping every resource, with IAM policies and quotas enforced per project.Source |
| Declarative deploymentTemplates that provision agent resources as one stack. | Formations provision providers, memories, tools, agents, orchestrations, and webhooks from one template, resolving refs into a dependency graph with tracked operations.Source |
| Versioning & rolloutAgent versions, canary rollout, gated promotion. | Every config change is archived as an append-only agent version, with canary rollout to a slice of traffic and eval-gated promotion.Source |
| Skill learningAgents authoring reusable skills from their own experience. | Memories and knowledge store retrievable context, but agents do not author or refine reusable skills from their own experience. |
Each solution is rated per capability cluster: Native (built into the product), Partial (covered with significant caveats or by adjacent services), Via plugin (possible through the solution's extension system), or Absent. Every non-absent rating links to its source, and every entry carries a verification date. Ratings compare product scope, not quality — a framework is not worse for delegating governance; it is a different archetype.
Spotted an outdated claim, or want a solution added? Open a pull request against ttoss/soat — each solution is one JSON file under packages/website/src/data/solutions/, validated in CI.