Tembo
Cloud execution platform for coding agents you already use, running Claude Code, Codex, Cursor, OpenCode, Amp and Pi across repositories on signals from GitHub, Linear, Jira, Sentry and Slack, self hostable in your own cloud.
Tembo began as a managed Postgres company. It does not sell a coding agent of its own. Customers bring the agents and Tembo provides the platform. It runs Claude Code, Codex, Cursor, OpenCode, Amp, Pi and fx inside isolated cloud VMs preloaded with your dependencies and tools, and orchestrates them across repositories, tickets and teams, dozens at once. The model and the agent remain the customer's choice, and the execution layer is the product. Project snapshots and warm pools start an environment in about two seconds.
Work arrives from signals rather than prompts. Agents are triggered by events in GitHub, GitLab, Bitbucket, Linear, Jira, Confluence, Sentry, Slack and HubSpot, run on cron schedules, start from a webhook or the API, or pick up an issue assigned to Tembo. Twelve agent templates cover recurring jobs such as changelogs, standup summaries, test pruning and turning feature requests into tickets, and a skills marketplace adds reusable skills.
A REST API, a TypeScript SDK, a CLI that pairs your own machine and a hosted MCP server let other systems create and run agents, and about forty MCP integrations reach databases, analytics, payments and cloud browsers. Each sandbox also ships Chromium and a desktop, so agents browse sites and operate graphical apps while a person watches.
Every run ends with a pull request or an artifact the team reviews, nothing merges until a person makes the call, and Tembo Review reviews pull requests as its own product. Every session lands in an audit trail, kept 90 days by default with SIEM export, and a transcript export records each tool call. Deployment is a choice between Tembo's cloud, hosted in the United States, and self hosting the platform as a NixOS image on AWS, Azure or GCP, which the docs call early access.
Tembo lists SOC 2, ISO 27001, ISO 42001, GDPR and HIPAA, with reports under NDA. Access runs through SSO over SAML and OIDC, role based access and scoped API keys with an audit trail, and sessions are isolated.
From our cloud coding agents video
Devin, Factory, Jules, OpenHands: What Each Cloud Coding Agent Does Best
Our video on the 11 cloud coding agents in the index names what each one does best. For Tembo, that is speed to a running session for the agents you already pay for.
The player starts at Tembo's part, 5:53 in. Recorded in October 2026; the profile here is live and updates as research is verified.
Vendor details
Canonical URL
https://www.tembo.io
Category
Coding agent
Subcategory
Coding agent orchestration platform (bring your own agent)
Funding status
Independent. Tembo was founded in 2022 as a managed Postgres company and raised its Series A in that era, then pivoted to coding agent orchestration in May 2025 and shut down its managed Postgres cloud. Reported funding totals of $14M and $20M both predate the current product, so neither reflects capital raised behind the agent platform. Tembo Max launched January 2026 at $200 per month alongside Tembo Proxy. legacy.tembo.io still shows the old Postgres copy with no sunset notice, unlinked from the main site.
Company status
independent
Use cases & customers
Primary use cases
Target customers
Deployment options
Integrations
A managed control plane that runs other vendors' coding agents rather than shipping one. Named supported agents are Claude Code, Cursor Agent, Codex, Amp, OpenCode, Pi and fx, executed in secure cloud environments preloaded with the customer's own dependencies and tooling. Named integrations span source control with GitHub, GitLab and Bitbucket, ticketing with Linear and Jira, docs with Confluence and Notion, chat with Slack and Microsoft Teams, error monitoring with Sentry, and Datadog, HubSpot, Snyk, BigQuery, AWS and Tailscale, plus a catalog of about forty MCP servers and custom MCP servers over HTTP, SSE or stdio. These act as both trigger surfaces and context sources, so a Sentry alert or a Linear ticket starts a run and supplies its context, while Datadog is a query integration rather than a trigger. Runs can also be scheduled on a cadence or fired from webhooks. Output is a draft pull request, including coordinated changes spanning multiple repositories in one pass with one PR per repository. Twelve agent templates cover recurring work such as release notes from commits, Sentry triage into Slack and documentation sync. The whole platform self hosts on the customer's own AWS, Azure or GCP in early access.
In practice
You already pay for Claude Code, Codex and Cursor and do not want a fourth agent. Tembo runs the agents you have inside one orchestration layer rather than replacing them.
Work should start from a Sentry alert or a Linear ticket, not from someone typing a prompt. Tembo is triggered by those signals and coordinates across multiple repositories.
Your security review blocks cloud only tools. The entire platform self hosts inside your own VPC.
Sources & related URLs
Related / legacy domains
Agentic Index coverage score
12.0 / 14 capabilities · 86%
| Integrations & Tool Calling | Full |
|---|---|
|
Named integrations cover GitHub, GitLab and Bitbucket for source control, Linear, Jira and Confluence for tickets and docs, Slack and Microsoft Teams for chat, Sentry for errors, and Notion, HubSpot, Snyk, BigQuery, AWS and Tailscale, plus a catalog of about forty MCP servers and custom MCP servers over HTTP, SSE or stdio. The same connections assemble agent context and return pull requests as output. Datadog is reachable as an MCP query integration only, not as a trigger, although the homepage lists it among trigger sources. Environments are preloaded with the customer's own dependencies and tools so agents reach the real toolchain. Sourcedocs.tembo.io/integrations, docs.tembo.io/integrations/datadog and tembo.ioread 2026-10-28 |
|
| Workflow Orchestration | Full |
|
Tembo is a managed control plane that runs other vendors' coding agents, Claude Code, Codex, Cursor, OpenCode, Amp, Pi and fx, as background agents, dozens at once, each session on its own VM. A multi repository session opens one pull request per repository, runs can be scheduled on a cadence, related triggers continue one session, and sessions can be forked. Tembo positions it as the layer above individual agents rather than one agent in one session, and no sub agent mechanism of its own is documented. Sourcedocs.tembo.io/features/agents, tembo.io/agents and tembo.io/changelog 2 October 2026read 2026-10-28 |
|
| Knowledge Grounding & RAG | Partial |
|
Projects snapshot cloned repositories with dependencies installed so agents start with the codebase ready, and rule files (tembo.md, AGENTS.md, CLAUDE.md and others) are read at the start of each session. Context for a run is assembled from the repositories plus Linear, Jira, Sentry, Slack and GitHub. Tembo documents no codebase index, knowledge graph, embeddings layer or retrieval surface of its own; deep codebase understanding within a run comes from the hosted agent. Sourcedocs.tembo.io/features/projects, docs.tembo.io/features/rule-files and docs.tembo.io/integrationsread 2026-10-28 |
|
| Human Oversight & Guardrails | Partial |
|
Every run ends with a draft pull request or an artifact the team reviews, and the review page says nothing merges until a person makes the call. A planning mode was added in September 2026 and the API accepts a normal or planning mode, and since October a browser notification fires when an agent needs approval, but no docs page describes an approval gate, a permission policy or per tool control, and the GitHub integration docs say agents can merge or close pull requests through tool calls. The per team, repository or agent approval gates appear only on the enterprise page. The gate is the customer's own pull request review. Sourcetembo.io/review, tembo.io/changelog 9 September and 9 October 2026, docs.tembo.io/integrations/github and tembo.io/enterpriseread 2026-10-28 |
|
| Security, Identity & Governance | Full |
|
Tembo's security and enterprise pages list SSO over SAML 2.0 and OIDC with Okta, Azure AD, Google Workspace or any compliant IdP, role based access at team, repository and agent level, API keys with scoped permissions, expiry, rotation and revocation, AES-256 at rest and TLS 1.3 in transit, and SOC 2 Type II, ISO 27001, ISO 42001, GDPR and HIPAA with reports under NDA. The vendor's own surfaces disagree on the attestation: the security page shows both a Type II claim and a Type I badge, and the trust center lists SOC 2 Type 1 and Type 2 behind a request while its self assessment says the company is working on its security compliance, so the attestation type is not relied on. The docs carry no SSO or SAML page, only organization member roles through the API. Sourcetembo.io/security, tembo.io/enterprise, trust.tembo.io and docs.tembo.io/apiread 2026-10-28 |
|
| Observability & Auditability | Full |
|
Every agent session has a centralized audit trail with configurable retention (90 days by default) and SIEM export on the security page, and the enterprise page says each prompt, agent action, file change and approval is logged. In the docs, session events and agent runs are retrievable through the API, Insights reports usage by provider, and a transcript export added on 23 October 2026 gives the full tool call record of a session as Markdown or JSON with secrets scrubbed. Sourcetembo.io/security, tembo.io/enterprise, docs.tembo.io/api and tembo.io/changelog 23 October 2026read 2026-10-28 |
|
| Memory & State Persistence | Partial |
|
Project snapshots persist the customer's dependencies and tooling across runs so agents do not rebuild the environment each time, related triggers continue one session, and sessions can be forked. The enterprise page says session history powers memory that compounds over time, but the docs describe no memory page, scope, lifetime or purge path, and scheduled automations keep state only through getAgentState and setAgentState tools. Any cross session memory sits with the hosted agent or a third party MCP server such as Supermemory. Sourcedocs.tembo.io/features/projects, tembo.io/enterprise and tembo.io/changelog 21 November 2025read 2026-10-28 |
|
| Deployment & Data Residency | Full |
|
In Tembo's cloud each session runs on a dedicated ephemeral Linux VM, and the subprocessor list puts the hosted servers on AWS and Leaseweb in the United States with no region choice. Customers can instead self host the platform as a NixOS image on AWS, Azure or GCP, documented as early access and sales led, and the enterprise page adds bare metal, on premises and air gapped options, though the self hosting docs say updates need outbound HTTPS. Sourcedocs.tembo.io/features/self-hosted/overview, docs.tembo.io/features/sandbox/overview, tembo.io/self-hosted and tembo.io/enterpriseread 2026-10-28 |
|
| Prebuilt Agents, Templates & Packs | Full |
|
Twelve agent templates are published at tembo.io/agent-templates and picked in the app with Use template, and the API lists reusable agent templates with their instructions and required parameters. Ready agents are named by cadence and job, such as daily changelogs, standup summaries, Test Pruner and turning feature requests into Linear tickets. Seven built in skills ship in every sandbox, and repository and managed skills are browsed in a skills marketplace in Settings and through the API. Sourcetembo.io/agent-templates, docs.tembo.io/features/agents and docs.tembo.io/features/agent-skillsread 2026-10-28 |
|
| Triggers & Channel Coverage | Full |
|
Agent triggers fire on events from GitHub, GitLab, Bitbucket, Jira, Linear, Sentry (issue created), Slack (message or reaction), Confluence and HubSpot, on cron schedules in UTC, and on a webhook or API POST to the runs endpoint. A developer can also mention @tembo in a thread, use a macro, or assign a Linear, Jira or GitHub issue to Tembo and receive a pull request back. Datadog is not a trigger source. Sourcedocs.tembo.io/api/v1/agents/create-an-agent-trigger, docs.tembo.io/integrations/linear and tembo.io/automationsread 2026-10-28 |
|
| Model Flexibility & Routing | Full |
|
The customer chooses the agent and the model per agent and per session from Anthropic, OpenAI, Google, xAI, Z.ai, Cursor, Fireworks, MiniMax and DeepSeek models on Tembo's gateway, or brings its own keys for OpenAI, Anthropic, xAI, Cursor, Amp, OpenRouter, Bedrock or Vertex, or connects a Claude, ChatGPT or SuperGrok subscription. Tembo ships no model of its own, so model and agent choice stay with the customer. Sourcedocs.tembo.io/features/models, tembo.io/pricing and tembo.io/changelog 2 October 2026read 2026-10-28 |
|
| APIs, SDKs & MCP Extensibility | Full |
|
The Tembo REST API at api.tembo.io, with an OpenAPI spec and keys the customer creates, rotates, expires and revokes at 100 requests a minute, creates sessions, manages repositories and projects, and creates, schedules, triggers and runs agents. A TypeScript SDK (@tembo-io/sdk) wraps it, the tembo CLI pairs the customer's own machine as a device, and Tembo's own MCP server at mcp.tembo.io/mcp connects AI clients to the same API with OAuth or a key. The older tembo.io/mcp page still describes a stdio task management server. Sourcedocs.tembo.io/api, docs.tembo.io/api/mcp and tembo.io/blog 24 September 2026read 2026-10-28 |
|
| Testing, Debugging & Optimization | Partial |
|
Tests, lint, type checks and builds run before work returns, a failed workflow auto fix and a Test Pruner template work the customer's own test suite, and agents execute in environments preloaded with the customer's real dependencies rather than a stripped sandbox. Those test the customer's code. There is no evaluation harness, benchmark suite or regression testing for agent behavior, and the GitHub integration docs say self verification is not covered. Sourcetembo.io/review, docs.tembo.io/integrations/github and tembo.io/agent-templatesread 2026-10-28 |
|
| Browser & Computer Use | Full |
|
Each sandbox ships Chromium 143, VS Code and a desktop with a built in agent-browser skill that automates browser interactions and takes screenshots, and the tembo browser open command. Agents use it to browse sites and operate graphical apps, screen recording captures the run, and a Computer preview streams the desktop at 60 frames a second so a person can watch. Sourcedocs.tembo.io/features/sandbox/built-in-skills-and-tools and tembo.io/blog 15 September 2026 (Tembo Computer)read 2026-10-28 |
|
The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded
Product updates
Admins can create custom roles from Settings > Members > Roles, choosing what each role can view or edit across sessions, pull requests, agents, integrations and billing, and set any role as the default for new members and invitations. The app hides or disables actions a member's role does not allow. The desktop app can also now import existing local conversations from Codex, Claude Code and Devin.
Bears on: Security / enterprise
View sourceA Device tab now opens in the session whenever an agent works on one of the user's paired machines, showing that machine's screen live as the agent clicks, types and runs things. The same update adds Google Docs, Google Sheets and Google Drive MCP servers, so agents can update documents, write values and formulas in spreadsheets, and search, create and copy files in Drive.
Bears on: Browser/computer use
View sourceWhen Claude or Codex needs a decision in the middle of a run, it now asks inside the Tembo session, and the user picks one of its options or types an answer so the agent can carry on. Projects can also keep a few sandboxes warm on a schedule, such as weekdays 9 to 5, so new sessions start instantly. That warm pool compute appears on the usage page.
Bears on: Human approval / guardrails
View sourcePricing
Pro $60 a month and Max $200 a month, each a usage allowance, for up to 5 and 10 users, with priority support on Max. Overage is billed on VM compute per hour and on model tokens. Enterprise is custom, and a free trial covers up to 10 users.
A monthly usage allowance per plan, drawn down by VM compute time and model tokens, with overage billing beyond it.
Included quota
Pro buys a $60 monthly allowance for up to 5 users with sandboxes up to Medium. Max buys a $200 allowance for up to 10 users with sandboxes up to XL, priority support and warm pools. Enterprise is custom.
What is public
Tembo publishes its plans and rates at tembo.io/pricing. A free trial includes a usage allowance for up to 10 users, unlimited repositories and projects, and priority support. Pro is $60 a month as a usage allowance for up to 5 users, Max is $200 a month for up to 10 users with priority support, and Enterprise is custom. VM compute rates run from $0.1066 an hour for Nano to $2.9536 an hour for Ultra, metered by the second, and model prices are listed per million tokens for Anthropic and OpenAI models. Customers can bring their own agent or API keys, or use a Claude, Codex, ChatGPT or SuperGrok subscription. There are no one time credit packs or fixed credit counts.
Billing mechanics
A monthly plan price buys a usage allowance of the same dollar amount. VM time and model tokens draw it down, and overage is billed beyond it. Bringing your own agent subscription moves model cost to that subscription.
Cost watchouts
The agents themselves are a separate cost. Tembo runs the Claude Code, Codex or Cursor subscriptions a team already pays for and includes no agent of its own.
Variable cost rationale
Tembo meters VM compute by the second while a VM runs, at hourly rates from $0.1066 for Nano to $2.9536 for Ultra across seven sizes (Nano, Micro, Medium, Large, XL, XXL, Ultra), and model tokens through its gateway at per million token prices, for example $11.50 in and $57.50 out for Claude Fable 5. The bill grows with the number and length of agent runs, the VM size and the model used. Because Tembo runs other vendors' agents, the agent a team picks also shapes how much compute a run takes. The plan price is a monthly allowance paid up front, and overage beyond it is billed with configurable spend limits on paid plans. Stopped and snapshotted VMs accrue no compute charges, and bringing an agent subscription or API keys moves model cost to that subscription while VM time still draws the allowance.
Additional watchouts
Usage is metered on both VM time and model tokens, so long sessions or large VMs draw the allowance down quickly. The agents themselves may be a separate subscription.
Overage / add-ons
Each plan's price is a monthly usage allowance. Usage beyond it is billed as overage at the published VM compute rates (metered by the second while a VM runs) and per million token model prices, with configurable spend limits on paid plans.
Sales call required
No, self serve available
Free / trial
Free trial with an included usage allowance for up to 10 users, sandboxes up to XL and no overage; the allowance amount and trial length are not stated.
Lowest paid plan
Pro at $60 per month, a usage allowance for up to 5 users
Commercial notes
Tembo does not sell an agent, so a customer keeps paying for Claude Code, Codex or Cursor separately and pays Tembo for the execution layer. Teams already standardized on those tools keep their own agent and model choice.
Key ambiguities
Pro and Max each buy a dollar allowance equal to the plan price ($60 or $200 a month), drawn down at the published VM and token rates, so the hours or tokens it covers depend on the VM size and model. Enterprise and self hosted pricing are custom.
Support SLA / resale
Priority support on Max and the free trial. Enterprise adds dedicated support, SLA guarantees and SSO.
Missing data
Enterprise and self hosted pricing are custom, and no figure is published for either.
Related vendors
- Cognition — Maker of Devin, an autonomous AI software engineer
- 10Web — Agentic website platform whose AI agents build, host and manage…
- AgentUI — Managed AI app builder for operations teams that generates and hosts…
- Aider — Open source, model agnostic terminal coding agent that edits your…
- Amp — Amp is a coding agent from Amp Frontier Corporation that runs each…
- Anthropic Claude Code — Anthropic's agentic coding system across terminal, desktop, IDE, web…
Alternatives to Tembo
The closest documented capability profiles to Tembo among coding agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- Capy12.5 / 14Fuller documented coverage on Human Oversight & GuardrailsTembo vs Capy →
- Cursor12.5 / 14Fuller documented coverage on Human Oversight & Guardrails
- Google Antigravity12.5 / 14Fuller documented coverage on Human Oversight & Guardrails
- Amp12.0 / 14Fuller documented coverage on Human Oversight & Guardrails
- Base4413.0 / 14Fuller documented coverage on Human Oversight & Guardrails and Memory & State Persistence
- Cline12.0 / 14Fuller documented coverage on Human Oversight & Guardrails
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded