Agentic Index
Stacklok vs TrueFoundry (2026)
Both vendors last verified
Stacklok and TrueFoundry both put a gateway between AI agents and the tools and models they call, and they split on where it runs and how much of the agent they handle. That verdict is the Agentic Index coverage score, graded from each vendor's own published materials.
Stacklok runs only in your own Kubernetes cluster, installed as one Helm chart and air gapped if needed, and the company never hosts customer data. Its open source ToolHive runs each MCP server in an isolated container with its own permissions and secrets. Stacklok Enterprise adds a Connector Gateway that carries the identity of the person behind every tool call, and an AI Gateway that routes models, caps spend per user or group in dollars and screens prompts.
TrueFoundry offers its AI Gateway and MCP Gateway as managed SaaS in a region you choose, or self hosted on AWS, GCP, Azure, OpenShift or on premises. Its MCP Gateway pauses tools flagged as destructive for a person to approve, and its TrueForge harness builds and runs agents with cost and tool calls traced per session.
TrueFoundry publishes its prices, with a free Developer tier and Pro at $25 per user a month, while Stacklok Enterprise is quoted.
Choose Stacklok to keep every tool and model call inside your own cluster. Choose TrueFoundry for a hosted gateway with approvals and an agent harness built in.
On the Agentic Index agent infrastructure ranking, neither Stacklok nor TrueFoundry clears the bar, which asks for all five production contract capabilities documented in full. Neither documents testing, debugging and optimization in full. 33 of the 186 vendors in the lane clear it. See the agent infrastructure ranking
This comparison is published by Agentic Index, an independent agentic AI vendor research platform. Stacklok and TrueFoundry are each graded against the same 14 capability Agentic Index taxonomy, from the vendor's own public materials under the Agentic Index verification standard, alongside 1,140 researched vendors. No vendor pays for placement and no vendor has reviewed this page. How this evidence is graded
Choose Stacklok if
- Nothing can leave your cluster. Stacklok installs as one Helm chart on your Kubernetes, runs air gapped, and the company neither hosts nor processes customer data.
- You want MCP servers sandboxed one by one. ToolHive, free under Apache 2.0, runs each server in its own container with its own permissions and secrets, as a desktop app, CLI or Kubernetes operator.
- Tool calls must carry a person's identity. The Connector Gateway brokers credentials per user from Okta or Microsoft Entra ID groups, so every call is traced to the person behind it.
- Model spend and data leaks worry your security team. The AI Gateway caps spend per user or group in dollars, screens prompts for injection, scans for card and personal data and forwards audit events to a SIEM.
- Your platform team wants a supply chain it can verify. Stacklok ships with Sigstore signatures, SLSA provenance and SBOMs, and it is led by Craig McLuckie and Joe Beda, who co created Kubernetes.
Choose TrueFoundry if
- You want to start without a sales call. The Developer tier is free for up to 3 users, and Pro is $25 per user a month with 20,000 requests and MCP tool calls per user included.
- Risky tools should wait for a person. The MCP Gateway pauses tools flagged as destructive until someone approves them, and it runs OAuth per user.
- You also need somewhere to build and run agents. TrueForge, an MIT licensed harness, draws on gateway models, MCP tools and a versioned Skills Registry and runs code in an isolated sandbox.
- Finance wants spend by team and by agent. Every agent session is traced with cost, tokens and tool calls, and a usage directory ranks users, teams and agents by spend.
- You want a managed service now and the option to self host later. TrueFoundry runs as SaaS or on AWS, GCP, Azure, OpenShift or on premises, and names NetApp, NVIDIA and Aviva as customers.
| Feature | S Stacklok |
T TrueFoundry |
|---|---|---|
| Action & orchestration | ||
|
Integrations & Tool Calling Ability to connect agents to real systems through native integrations, OAuth-authenticated actions, custom tools, APIs, webhooks, or MCP-compatible tools. |
||
|
StacklokIntegrations & Tool Calling Every tool call carries the identity of the person who made it. Administrators register MCP servers as connectors in the Connector Gateway, an identity aware endpoint for MCP tool calls, and grant them to directory groups. The gateway then brokers each connector's credentials on the caller's behalf. ToolHive runs each MCP server in an isolated container with its own permissions and secrets, and a Virtual MCP Server aggregates backends into one endpoint with tool filtering for a given agent. Sourcedocs.stacklok.com/connector-gatewayread 2026-11-03 |
||
|
TrueFoundryIntegrations & Tool Calling MCP servers registered in TrueFoundry's MCP Gateway are listed in the agent builder, where the customer picks the individual tools each agent sees. The gateway holds the credentials, runs per-user OAuth flows and refreshes tokens, and in the gateway playground a model uses a connected MCP server to act on outside systems such as a calendar or a database, so agents call into external systems through a governed tool layer. Sourcetruefoundry.com/docs/agent-platform/agent-harness/what-truefoundry-addsread 2026-11-03 |
||
|
Workflow Orchestration Ability to sequence, branch, retry, route, and combine deterministic workflow nodes with autonomous agent steps. |
||
|
StacklokWorkflow Orchestration A Virtual MCP Server aggregates backend MCP servers behind one endpoint with static backend selection, tool filtering and renaming. The Connector Gateway exposes a toolset scoped to a group. Both route a call to the right server instead of running work. The platform runs no workflow or agent loop of its own, and there is no sequencing, branching or retrying across deterministic workflow steps and autonomous agent steps. Sourcedocs.stacklok.com/connector-gatewayread 2026-11-03 |
||
|
TrueFoundryWorkflow Orchestration Planning, tool calls, context management, approvals and state all run in the agent's execution loop inside TrueFoundry's hosted agent harness, which delegates focused subtasks to parallel subagents and can chain MCP tool calls in a single sandbox script. There are no deterministic workflow nodes, branching or retry paths that a run can combine with those autonomous steps. Sourcetruefoundry.com/docs/agent-platform/agent-harness/overviewread 2026-11-03 |
||
|
Triggers & Channel Coverage How agents wake up and where they work: schedules, webhooks, message events, CRM events, inbox events, chat, email, voice, and collaboration tools. |
||
|
StacklokTriggers & Channel Coverage A client or agent calling a tool or a model is what sets the platform to work. ToolHive runs the servers and the gateways broker the calls, both at the caller's request. No schedule, event, webhook or inbound queue starts an agent run, and nothing wakes an agent unless a person or client starts the work. Sourcedocs.stacklok.com/toolhiveread 2026-11-03 |
||
|
TrueFoundryTriggers & Channel Coverage Agents, sessions and schedules live in the platform through TrueFoundry's hosted agent harness, shared with the organization under the same authentication and access control as the rest of TrueFoundry. A schedule sends work to an agent without a person starting it. Sourcetruefoundry.com/docs/agent-platform/agent-harness/what-truefoundry-addsread 2026-11-03 |
||
| Knowledge & context | ||
|
Knowledge Grounding & RAG Ability to ground agent behavior in company data through document ingestion, retrieval, external knowledge APIs, semantic search, or RAG layers. |
||
|
StacklokKnowledge Grounding & RAG The vMCP optimizer searches tool descriptions to surface only the relevant tools for each request and cut token use. The registry catalogs MCP servers and skills. There is no index, graph or embeddings layer over the customer's own documents. Sourcedocs.stacklok.com/toolhive/guides-vmcp/optimizerread 2026-11-03 |
||
|
TrueFoundryKnowledge Grounding & RAG Chat, embedding and rerank model calls route through TrueFoundry's AI Gateway, so a customer can run its own retrieval through the gateway, but TrueFoundry maintains no document ingestion, index or retrieval layer over the customer's content. The Skills Registry holds versioned skills, not the customer's documents. Sourcetruefoundry.com/docs/ai-gateway/playground-overviewread 2026-11-03 |
||
|
Memory & State Persistence Ability to persist context across a run, conversation, workflow, user, team, or longer-term memory layer. |
||
|
StacklokMemory & State Persistence The product runs and governs MCP servers, skills and model traffic. None of its components (the ToolHive runtime, Registry Server, vMCP, Connector Gateway, AI Gateway and Enterprise Manager) persists an agent's state or a user's context across runs, so agents get no memory from it. Sourcedocs.stacklok.com/toolhiveread 2026-11-03 |
||
|
TrueFoundryMemory & State Persistence Agent state and context are managed by TrueFoundry's hosted agent harness, which keeps sessions in the platform under the organization's access control and summarizes older history when context nears the model's limit. That is session memory, scoped by the platform's access control. There is no long term memory layer and no way to review, edit or delete what an agent remembers. Sourcetruefoundry.com/docs/agent-platform/agent-harness/overviewread 2026-11-03 |
||
| Control & trust | ||
|
Human Oversight & Guardrails Approval steps, consent checkpoints, escalation rules, structured guardrails, policy constraints, and pause/resume controls. |
||
|
StacklokHuman Oversight & Guardrails Administrators limit what an agent may do instead of putting a person in the loop. They decide which MCP servers are registered as connectors and which directory groups may use them. Enterprise Manager policies can block servers that are not in the approved registry, and authorization policies limit each role's tools. The AI Gateway screens prompts for injection and scans requests and responses for card and personal data. The customer controls all of these limits, but no person reviews, approves or validates an agent action before it commits. Sourcedocs.stacklok.com/connector-gatewayread 2026-11-03 |
||
|
TrueFoundryHuman Oversight & Guardrails Tools flagged as destructive at TrueFoundry's MCP Gateway automatically pause for human approval in every agent, so a team gates a destructive action once, centrally, rather than per agent. The hosted agent harness, TrueForge, pauses a run for tool approval or asks the user a structured question before it continues, and guardrails such as Cato Networks can validate or change LLM requests and MCP tool calls. The gate is shipped, and it holds the agent's action until a person decides. Sourcetruefoundry.com/trueforgeread 2026-11-03 |
||
|
Security, Identity & Governance RBAC, SSO, auditability, encryption, least-privilege tool access, compliance posture, and data handling policy. |
||
|
StacklokSecurity, Identity & Governance Identity comes from Okta or Microsoft Entra ID, with SCIM provisioning into a directory of users, groups and subgroups. Virtual API keys are bound to a user's identity. Enterprise authorization uses fleet wide MCP roles in RBAC custom resources, with delegation at the namespace level, and Cedar policies apply to MCP servers. Connector credentials are stored encrypted at rest in the directory. The distribution itself carries Sigstore signatures, SLSA provenance and SBOMs the customer can verify. Stacklok holds no third party attestation of its own operations and says none applies to a self hosted product that holds no customer data. Sourcestacklok.com/security-centerread 2026-11-03 |
||
|
TrueFoundrySecurity, Identity & Governance TrueFoundry SaaS maintains SOC 2 Type II, GDPR and HIPAA programs, with reports and trust documentation at trust.truefoundry.com, and customers get single sign-on over SAML or OIDC with SCIM provisioning, role-based access control across users, teams and virtual accounts, and personal and application tokens with lifetime and rotation controls. Sourcetruefoundry.com/docs/platform/saas-securityread 2026-09-21 |
||
|
Observability & Auditability Traces, logs, execution histories, metrics, audit events, and debugging detail for production agent behavior. |
||
|
StacklokObservability & Auditability The AI Gateway records structured audit events for model requests, detections and key actions and forwards them to the customer's SIEM. The Connector Gateway's tool usage view shows traffic by time range, connector and tool. An Enterprise Manager telemetry policy enforces OpenTelemetry settings across Stacklok clients, so tool calls are traced into the customer's own stack. A customer can inspect what an agent sent and received, keep audit events apart from traces, and export both to its own tools. Sourcedocs.stacklok.com/ai-gateway/forward-audit-logsread 2026-11-03 |
||
|
TrueFoundryObservability & Auditability Every agent session on TrueFoundry is captured with cost, tokens, turns, tool calls and a turn-by-turn transcript, with traces per run covering model calls, tool calls, sandbox executions and subagents, and it inherits the AI Gateway's request logs, analytics, OpenTelemetry export and Prometheus and Grafana. Audit logging of platform activity is available by dashboard and API, and request logs and traces follow the retention the customer configures. That shows what the agent did step by step, with an audit trail separate from runtime traces. Sourcetruefoundry.com/docs/agent-platform/agent-harness/what-truefoundry-addsread 2026-11-03 |
||
|
Deployment & Data Residency Deployment modes and options, including SaaS, dedicated cloud, VPC, on-prem, hybrid, local runtime, and self-hosting. |
||
|
StacklokDeployment & Data Residency Everything runs inside the customer's own infrastructure. Stacklok Enterprise deploys as a single umbrella Helm chart into the customer's Kubernetes cluster. Distributed deployments can span several clusters, and an air gapped install mirrors the chart from a private registry. Stacklok neither hosts nor processes customer data. Sourcedocs.stacklok.com/platformread 2026-11-03 |
||
|
TrueFoundryDeployment & Data Residency On TrueFoundry's managed SaaS the customer chooses the region the AI Gateway is deployed in and where request logs and traces are stored, and can bring its own Amazon S3, Azure Blob or Google Cloud Storage so logs and traces stay in its own buckets. The control plane and gateway also install self-hosted on AWS, GCP, Azure, OpenShift or on-prem, and the Enterprise plan includes VPC, on-prem and air-gapped deployment. So the customer both picks the region and can run the platform in its own environment. Sourcetruefoundry.com/docs/platform/saas-securityread 2026-11-03 |
||
| Solution readiness | ||
|
Prebuilt Agents, Templates & Packs Ready-made workflows, packaged employees, templates, blueprints, industry solutions, and role-specific agents that reduce time-to-value. |
||
|
StacklokPrebuilt Agents, Templates & Packs Agent skills ship with ToolHive. They are reusable bundles of tools, permissions and secrets that a customer browses in a registry and installs into its AI clients. A skill can be built from a local folder as an OCI artifact, then published, listed or deleted through the Registry Server's admin API. The CLI and desktop UI also install, distribute and manage skills. Sourcedocs.stacklok.com/toolhive/guides-registryread 2026-11-03 |
||
|
TrueFoundryPrebuilt Agents, Templates & Packs Agents draw on a versioned catalog of skills in TrueFoundry's Skills Registry, and its Agent Registry records the customer's own agents. Neither is a catalog of prebuilt agents a customer adopts, and TrueFoundry offers no agent templates or packaged agents. Saved prompts serve as the customer's own templates. Sourcetruefoundry.com/docs/llms.txtread 2026-11-03 |
||
| Platform extensibility | ||
|
Model Flexibility & Routing Ability to work across multiple foundation models, route tasks to different models, or let buyers bring their own providers and keys. |
||
|
StacklokModel Flexibility & Routing Customers and admins decide which model serves a request. The AI Gateway is a self hosted control point between AI clients and model providers. The customer connects OpenAI, Anthropic, AWS Bedrock, Azure OpenAI, Google Vertex AI and OpenAI compatible providers. It then maps model names onto them with a default route, weighted load balancing, priority failover, retries and timeouts, declared as AIGateway and AIPolicy resources. Sourcedocs.stacklok.com/ai-gatewayread 2026-11-03 |
||
|
TrueFoundryModel Flexibility & Routing Every model enabled for a user in TrueFoundry's AI Gateway appears in the agent builder's model picker, grouped by provider, and switching models is a one-click change. The gateway playground lets teams browse and select chat, embedding, rerank and image models across providers, and virtual models back one logical name with several models for routing and failover. The customer chooses the model and the provider. Sourcetruefoundry.com/docs/agent-platform/agent-harness/what-truefoundry-addsread 2026-11-03 |
||
|
APIs, SDKs & MCP Extensibility Composability layer: stable APIs, SDKs, MCP tool consumption/serving, custom tools, and integration into internal systems. |
||
|
StacklokAPIs, SDKs & MCP Extensibility Builders get ToolHive, an Apache 2.0 open source platform with a CLI, desktop UI and Kubernetes operator. Its Registry Server implements the MCP registry API for servers, skills and plugins. Stacklok Enterprise publishes a REST API reference for the Enterprise Manager, Connector Gateway and AI Gateway. It also publishes custom resource definitions for authorization and a management API for budgets. Sourcedocs.stacklok.com/toolhiveread 2026-11-03 |
||
|
TrueFoundryAPIs, SDKs & MCP Extensibility TrueFoundry offers an API reference and OpenAPI specifications for the platform and the AI Gateway, a Python SDK and a CLI, and the gateway playground generates integration code for the OpenAI SDK, the REST API and cURL. Agents built in the hosted harness are reachable through its HTTP API and TypeScript SDK, so the platform can be called from outside through a documented API and SDK. Sourcetruefoundry.com/docs/llms.txtread 2026-11-03 |
||
|
Testing, Debugging & Optimization Testing, debugging, scoring, retries, fallbacks, quality gates, and optimization loops for improving agent workflows before and after deployment. |
||
|
StacklokTesting, Debugging & Optimization Before an MCP server goes to production, ToolHive's CLI can test and validate it. The registry applies review criteria before a server is listed. There are no scored test cases, pass rates or judge verdicts that give a readable result to compare one change against another. Sourcedocs.stacklok.com/toolhive/guides-cli/test-mcp-serversread 2026-11-03 |
||
|
TrueFoundryTesting, Debugging & Optimization Teams can test prompts, models, guardrails and MCP tools before production in TrueFoundry's AI Gateway playground, which shows a latency breakdown per request across the gateway and the model and saves versioned prompts, and the agent builder tests an agent against a live chat. There are no dataset runs or scoring of output quality. Sourcetruefoundry.com/docs/ai-gateway/playground-overviewread 2026-11-03 |
||
| Specialist automation | ||
|
Browser & Computer Use Browser, desktop, or remote/local computer control for workflows that cannot be handled through stable APIs alone. |
||
|
StacklokBrowser & Computer Use The product governs and runs MCP servers and model traffic, and drives no interface itself. It operates no browser, desktop or remote computer session for an agent, and no headless fetch or third party browsing engine is wired in. Sourcedocs.stacklok.com/toolhiveread 2026-11-03 |
||
|
TrueFoundryBrowser & Computer Use Code, file and shell execution run in an isolated sandbox that TrueFoundry's hosted agent harness provisions, and browser tools reach an agent only as MCP servers the customer registers in the gateway. TrueFoundry ships no browser, desktop or computer control of its own. Sourcetruefoundry.com/docs/agent-platform/agent-harness/overviewread 2026-11-03 |
||
Pricing snapshot
Sourced from the Index pricing dataset · open each vendor's profile for full detail.
| Pricing | S Stacklok |
T TrueFoundry |
|---|---|---|
|
Entry price Lowest public entry point |
Open source ToolHive free; Stacklok Enterprise quoted through sales | Free Developer tier. Pro is $25 per user per month. Enterprise is priced through sales. |
|
Pricing confidence How public the numbers are |
Contact only | Public, partial |
|
Billing Primary billing axis |
Annual Stacklok Enterprise subscription; open source core free | Per user, plus gateway requests and MCP tool calls above the included allowance. |
|
Variable cost Workload / overage exposure |
Low variable cost | High variable cost |
|
Free tier / trial Try before you buy |
Free tier
|
Free tierTrial
|
|
Buying motion Self-serve vs sales call |
Sales call | Mixed |
|
Pricing verified When this pricing was last checked |
Product updates
Newest first, each linked to its source.
Stacklok
-
· Security / enterprise
ToolHive v0.57.0 adds authorization scoped to each backend in its virtual MCP server, so access rules can differ for each MCP server sitting behind the gateway.
Source -
· Security / enterprise
ToolHive v0.53.0 adds group based upstream selection to the embedded auth server of its Virtual MCP Server.
Source -
· Integrations
Stacklok has introduced an integration with Anthropic MCP Tunnels to securely connect Claude to internal systems behind corporate firewalls.
Source
TrueFoundry
-
· Pricing / packaging
SaaS and hybrid customers can now add curated open weight and frontier models that run on TrueFoundry's own capacity, with no provider account to create and no API key to rotate.
Source -
· Integrations
TrueFoundry release 0.176.17 adds AWS Bedrock AgentCore as an agent registry integration that discovers, imports and syncs remote agents every hour.
Source -
· Human approval / guardrails
TrueForge 0.3.0, TrueFoundry's open source agent harness, adds an API for human approval and policy events during a turn, a durable inbox for them, and a way for a user to approve a tool for the rest of a session with an optional expiry.
Source
Neither Stacklok nor TrueFoundry publishes an enterprise price, so Stacklok Enterprise and TrueFoundry Enterprise both start with a quote. Stacklok governs what agents reach and records what they did, but it does not run agent workflows, hold memory or index documents. Mecatl, Stacklok's separate agent harness, is a different product. Stacklok describes guardrails and audit rather than an approval step a person signs off. TrueFoundry's managed service lists SOC 2 Type II, GDPR and HIPAA programs with reports on its trust site. Stacklok's case rests on never holding customer data and on a signed, verifiable distribution. Neither publishes a benchmark for its gateway's screening or routing. Stacklok is backed by Accel, Bain Capital Ventures and Madrona, and TrueFoundry is independent.
More comparisons with Stacklok or TrueFoundry
Other matchups in agent infrastructure platforms
Not the pairing you were after? These compare a different set of agent infrastructure platforms on the same 14 capabilities.