Back to vendors
P

Poolside

Also known as: Poolside Malibu, Laguna XS.2, Laguna M.1, Laguna XS 2.1, Laguna S 2.1, Fern Labs

Visit site
Entry priceEnterprise and government deployments are custom and not public, and the government offer is on premises inference with no per token fees. The open weight Laguna xs 2.1 and Laguna s 2.1 models are published, with per token access through OpenRouter and Vercel AI Gateway.Full pricing detail

Coding agent platform built on Poolside's own Laguna models, whose weights are published openly, with the pool CLI for developers and enterprise and government deployments inside the customer's boundary, including air gapped, where every agent action is recorded as a searchable trajectory.

Poolside is a full stack platform for enterprise software development, combining its own foundation models, developer tools, and a governed agent orchestration layer that runs entirely inside the customer's infrastructure. The company was founded in 2023 by Jason Warner, the former CTO of GitHub, and Eiso Kant. It trains its models with Reinforcement Learning from Code Execution Feedback, learning from running code, not only from reading it.

The Poolside Platform is the product the company now leads with. It runs production grade AI agents inside the customer's security boundary with full auditability and governance. Poolside builds it for teams whose approved base images are a matter of policy and whose network architecture ensures no single node has both GPU access and outbound connectivity.

The model line has two generations. Malibu handles deep reasoning, refactoring and test writing, while Point drives low latency completion. Both can be fine tuned on a customer's own codebase, documentation and knowledge bases. The newer Laguna family includes XS.2 and M.1, served at 256K context, and XS 2.1 and S 2.1 for longer horizon reasoning work, with S 2.1 serving up to a 1M token context. The Laguna S 2.1 and XS 2.1 weights are published openly, and Laguna XS.2 is free open weights for local agentic coding. Developers can also use the hosted platform free, work from the pool CLI, or chat with the models at chat.poolside.ai without signing up.

Above the models sits the Console, where teams build and govern single and multi agent systems running in isolated sandboxes. In one worked example, the Console takes a natural language specification, generates a working pipeline, pushes it to GitHub, builds it through an API and iterates until every step passes. Pipelines are code first and fully auditable, and meta pipelines review agent trajectories to refine how work gets done.

Poolside acquired Fern Labs, a London forward deployed research engineering firm, in November 2025 for Bridge, its multi agent orchestration layer for high stakes production environments. The Console runs Poolside's own models alongside third party models such as Claude and GPT, configured per agent through reusable provider settings.

Agents run where developers already work, in VS Code, Visual Studio, Zed, IntelliJ or the terminal. A macOS Desktop Assistant runs multiple agents across projects. They connect to Slack, Jira, GitHub, Workday and Salesforce through centrally managed MCP servers. An ACP interface invoked with pool acp lets external environments drive agent workflows.

Customers receive full model weights, not API access, and deploy the entire stack into an environment they control. The options are their own bare metal, a VPC on AWS, Azure or Google Cloud, Kubernetes or OpenShift clusters, or their own NVIDIA hardware via Helm. Partners including Dell supply air gapped turnkey hardware, from an on premises rack for hundreds of developers to a compact offline workstation for small classified teams. Nothing leaves the boundary, and there is no inference path out.

Administrators define boundaries centrally and the platform enforces them, with permission rules in which deny overrides allow. Sandboxes carry filesystem and network policies set before an agent starts. Credentials are encrypted at rest, injected at runtime and redacted from logs by pattern, and step limits are enforced per session. Every tool call, file edit, reasoning step and decision is recorded as a searchable, exportable trajectory with SIEM propagation. Government grade options add a hardened operating system and IL5 deployability. Poolside publishes no SOC 2, ISO 27001 or FedRAMP attestation, and it lists an authority to operate as achieved without naming the system or agency.

The company raised a $500M Series B in 2024 at a $3B valuation led by Bain Capital, DST Global and eBay, and in 2025 Nvidia committed up to $1B, lifting the valuation toward $12B. Around 150 people work across the US, UK and France, with defense customers including RTX. Poolside sells through Forward Deployed Research Engineers who embed with customer teams, so enterprise deployment is not self serve. Poolside does not publish enterprise pricing.

Vendor details

Canonical URL

https://poolside.ai

Category

Coding agent

Subcategory

Enterprise coding foundation models and governed agent platform

Funding status

Independent and heavily funded. Founded in 2023 by Jason Warner, former chief technology officer of GitHub, and Eiso Kant, Poolside raised roughly 126 million dollars in seed and early rounds, then a 500 million dollar Series B in October 2024 led by Bain Capital, DST Global, and eBay at a 3 billion dollar valuation. In October 2025 Nvidia announced an investment of up to 1 billion dollars, reported to lift the valuation toward 12 billion. The company had about 150 employees as of late 2025, headquartered in San Francisco with a Paris presence.

Company status

independent

Use cases & customers

Primary use cases

governed multi agent development pipelinesenterprise code generation and completionsovereign air gapped AI for defense and governmentcodebase fine tuned developer assistant

Target customers

large enterprises with strict security and compliance needsdefense, government, and regulated industriesengineering organizations wanting models and agents on their own infrastructure

Deployment options

Customer bare metal (on-premises)Air-gapped on turnkey hardware via partners including DellCustomer VPC on AWS, Azure or Google CloudKubernetes or Red Hat OpenShift clustersBring your own NVIDIA hardware via HelmOn-premises enterprise rack (hundreds of developers)On-premises tower / offline workstation (classified or constrained teams)Managed via Amazon BedrockLocal open-weight models (Laguna XS.2)

Integrations

Agents run where developers already work across VS Code, Visual Studio, Zed, IntelliJ and the terminal, plus a macOS Desktop Assistant running multiple coding agents across projects and repositories, a web assistant with conversation search, and the Poolside Console. Centrally managed, admin approved MCP servers connect Slack, Jira, GitHub, Workday and Salesforce, spanning chat, ticketing, source control, HR and CRM, alongside Linear and Notion. An ACP interface invoked with pool acp lets external development environments send prompts and run agent workflows. Public APIs are exposed and the models are available through a single API in Amazon Bedrock. Poolside has a strategic partnership with Redpanda's Agentic Data Plane. Agents act by editing files, running terminal commands, calling tools, building through APIs and pushing to source control inside governed sandboxes.

In practice

You are in defense or government and cannot send code off premises. Poolside delivers full model weights into your air gapped environment, so every query and agent action runs inside your boundary with nothing leaving.

You want agents that do real work under control. Through the Console you build multi agent pipelines in sandboxes with per agent permissions, step limits, and full trajectory audit trails, so automation stays governed.

You want a model tuned to your own code. Poolside fine tunes Malibu and Point on your codebase, documentation, and knowledge bases, and can route across its own and third party models per agent.

Agentic Index coverage score

11.0 / 14 capabilities · 79%

Integrations & Tool Calling Full

Agents connect through centrally managed MCP servers with admin-approved connections, including Slack, Jira, GitHub, Workday and Salesforce across chat, ticketing, source control, HR and CRM, as well as Linear and Notion. Native editor integration covers VS Code, Visual Studio, Zed and IntelliJ, plus a macOS desktop app and the terminal. Agents act by editing files, running terminal commands, calling tools, building through APIs and pushing to source control inside governed sandboxes. Poolside also has a strategic partnership with Redpanda's Agentic Data Plane.

Sourcepoolside.ai/blog/introducing-the-poolside-platform and poolside.ai/enterpriseread 2026-08-30

Workflow Orchestration Full

The Console builds and governs single and multi-agent systems running in isolated sandboxes. In a worked example, it takes a natural language specification, generates a working pipeline, pushes it to GitHub, builds it through an API and iterates until every step passes.

Pipelines are code-first and fully auditable, meta pipelines review agent trajectories to refine how work gets done, the Desktop Assistant runs multiple coding agents across projects and repositories in parallel, and step limits bound each run. Poolside acquired Fern Labs for Bridge, a multi-agent orchestration layer built for high-stakes production environments.

Sourcepoolside.ai/enterprise, poolside.ai/blog/fern-labs-acquisition and poolside.ai/blog/introducing-poolside-desktop-assistantread 2026-08-30

Knowledge Grounding & RAG Partial

Context is assembled per run. The agent reads the code in its working directory, runs commands, loads local skills and personal MCP servers, and uses built-in web_search and web_fetch tools.

AGENTS.md instructions at personal, project and directory scope are instructions the product applies, not a knowledge store, and there is no maintained retrieval structure over the customer's knowledge.

Fine-tuning Malibu and Point on the customer's codebase puts knowledge in the model weights, and the Git or S3 backed knowledge bases described on Poolside's former enterprise page do not appear in the current docs.

Sourcedocs.poolside.ai/agent-instructionsread 2026-09-29

Human Oversight & Guardrails Full

The pool CLI asks for approval before any tool call that no allow rule covers. The default approval mode, Always ask, prompts for every action not already allowed. Accept edits auto-approves workspace file changes and prompts for the rest, an Auto mode sends pending actions to a classifier and opens the normal approval dialog for high risk ones, and switching from Plan to Build always requires the user's review, even under Allow all. Deny rules always override allow, pool exec needs --unsafe-auto-allow to run without prompts, and sandboxes add file system and network boundaries.

Sourcedocs.poolside.ai/permissions, /cli/interactive-mode and /sandboxesread 2026-09-29

Security, Identity & Governance Full

Poolside lists ATO Achieved, a STIG hardened OS and IL5 deployability for government use, without naming the system or agency, and publishes no SOC 2, ISO 27001 or FedRAMP attestation. Administrators define boundaries centrally and the platform enforces them.

Sandboxes carry file system and network policy, and credentials are encrypted at rest, injected at runtime and redacted from outputs. A secrets store keeps raw values from agents, and permission rules with deny overriding allow govern what agents may read, write and run.

Role based access control over human and agent identities appeared on Poolside's enterprise page, which now redirects to the homepage.

Sourcepoolside.ai/government, poolside.ai/blog/introducing-the-poolside-platform, docs.poolside.ai/permissions and /secretsread 2026-09-29

Observability & Auditability Full

Every agent action is recorded as a searchable trajectory covering tool calls, file edits, reasoning steps and decisions, retained under configurable audit policy, propagated to SIEM and exportable for compliance and debugging.

The Console adds agent metrics for monitoring inference performance, including time to first token percentiles, along with agent dashboards, tracking of configuration changes over time, and console search across agents and recent activity, and the web assistant has search for finding conversations and navigating to related resources. Meta pipelines review agent trajectories to refine how work is done.

Sourcepoolside.ai/blog/introducing-the-poolside-platform and docs.poolside.ai/release-notes/march-2026read 2026-08-30

Memory & State Persistence Partial

Sessions persist and resume. The pool CLI opens a session picker to resume a previous session from the current directory, or resumes a specific session by the ID printed on exit with pool --resume, and prompt history is browsable per directory, so a run carries on where it stopped. No memory layer that the agent writes and reads across sessions is described, and AGENTS.md holds instructions, not memory. Trajectories retained under audit policy serve as an execution record.

Sourcedocs.poolside.ai/cli/interactive-mode and the docs llms.txt indexread 2026-09-29

Deployment & Data Residency Full

Poolside offers four deployment modalities, which include the customer's own bare metal, air-gapped operation on turnkey hardware through partners including Dell, and an existing VPC on AWS, Azure or Google Cloud. Kubernetes and Red Hat OpenShift are supported for teams already running container orchestration, with Helm-based installation onto customer NVIDIA hardware.

An on-premises rack serves hundreds of developers, and a compact offline workstation serves small classified teams. Customers receive complete control of model weights rather than third-party API access, so inference runs inside the boundary with no egress, and government-grade options include fully air-gapped operation, a hardened operating system and IL5 deployability. Models are also available managed through Amazon Bedrock.

Sourcepoolside.ai/blog/introducing-the-poolside-platform, poolside.ai/enterprise and docs.poolside.ai/release-notes/march-2026read 2026-08-30

Prebuilt Agents, Templates & Packs Partial

Local skills give agents task-specific instructions and resources, subagents come built in or custom with separate context, and the Platform's Console builds single and multi-agent pipelines that are code-first and reusable, delivered with Forward Deployed Research Engineers. There is no browsable library of prebuilt agents, template gallery or marketplace.

Sourcedocs.poolside.ai/skills, /subagents and poolside.ai/blog/introducing-the-poolside-platformread 2026-09-29

Triggers & Channel Coverage Full

Poolside runs in GitHub Actions on an event, a schedule or on demand. Example workflows review pull requests on on: pull_request, scan the repository nightly on a cron schedule and triage issues, so repository work does not wait for someone to open a terminal. It can also be invoked from the pool CLI, interactively, through pool exec for automated tasks or through ACP for editors, as well as from JetBrains, Zed, Neovim and any ACP compatible editor, Poolside Assistant in VS Code and Visual Studio, the desktop Assistant, and the API.

Sourcedocs.poolside.ai/tools/github-actions, /cli/pool and /toolsread 2026-09-29

Model Flexibility & Routing Full

The customer configures models per agent through reusable provider connection settings. Poolside's own models run alongside third party models including Claude and GPT, and the customer can bring its own provider. Poolside's own family spans Malibu, Point and the Laguna models, with Laguna S 2.1 serving up to a 1M token context, and the Laguna S 2.1 and XS 2.1 weights are published openly. Customers can fine tune models on their own codebase.

Sourcepoolside.ai, docs.poolside.ai supported-models and log-inread 2026-10-25

APIs, SDKs & MCP Extensibility Full

An ACP interface invoked with pool acp connects external development environments to send prompts, receive responses and run agent workflows. The platform hosts first-class MCP servers with admin-approved connections and exposes reusable model provider connection settings with connection testing, and trajectory data can be exported for debugging. Public APIs are available, the models can be reached through a single API in Amazon Bedrock, and deployment onto customer NVIDIA hardware is driven by Helm, with Kubernetes and Red Hat OpenShift supported. No named public SDK package is published.

Sourcedocs.poolside.ai/release-notes/march-2026 and poolside.ai/enterpriseread 2026-08-30

Testing, Debugging & Optimization Partial

Agents run the customer's tests and iterate until pipeline steps pass, pool reviews pull requests and scans repositories in GitHub Actions, and the Platform records searchable trajectories that meta pipelines review to refine how work is done. The models are trained with reinforcement learning from code execution feedback. These check the customer's code and improve Poolside's own models, and there is no harness or evals product for the customer to evaluate, replay or regression test agent behavior.

Sourcedocs.poolside.ai/tools/github-actions and poolside.ai/blog/introducing-the-poolside-platformread 2026-09-29

Browser & Computer Use Not documented

Agents work through programmatic interfaces, including containerized sandboxes with filesystem and network policies set before a run, terminal command execution covering builds, package installation and git, MCP tool calls to approved servers, source control APIs and editor extensions. There is no browser control, screenshot capture, visual verification or way to operate software that lacks a programmatic interface.

Sourcepoolside.ai/blog/introducing-the-poolside-platform and poolside.ai/enterpriseread 2026-08-30

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

·Agent capabilityPartially Verified

Poolside released Laguna S 2.1, a 118-billion-parameter Mixture-of-Experts foundation model optimized for agentic coding and extended reasoning. The open-weight model activates 8 billion parameters per token, features a 1-million-token context window, and introduces separate thinking modes while remaining compact enough to run on a single NVIDIA DGX Spark desktop machine.

Bears on: Agent capability

View source
·Agent capabilityVerified

Poolside released Laguna XS 2.1, a 33B-parameter Mixture-of-Experts model for agentic coding and local deployment, with improved SWE-bench Multilingual and terminal-task performance, multiple quantized checkpoints, and a move to the permissive OpenMDW-1.1 license.

Bears on: Agent capability

View source
View all 2 Poolside updates →Tracked since Jul 2026 · Verified from public vendor sources

Pricing

Enterprise and government deployments are custom and not public, and the government offer is on premises inference with no per token fees. The open weight Laguna xs 2.1 and Laguna s 2.1 models are published, with per token access through OpenRouter and Vercel AI Gateway.

Enterprise deployment is a custom contract sized to the environment and developer count, delivered with Forward Deployed Research Engineers. Poolside models are also available usage based in Amazon Bedrock, priced per token. The open weight Laguna xs 2.1 runs on device for free, as does the earlier Laguna XS.2 under an Apache license.

Free tier

Included quota

Enterprise brings the full platform inside the customer boundary: foundation models with full weights, the Console for agents and orchestration, IDE developer tools, sandboxed execution, and governance and audit. It deploys across a cloud VPC, an on premises rack, an offline tower or customer hardware, with Forward Deployed Research Engineer support. Amazon Bedrock offers managed Malibu and Point models billed per token. The open weight Laguna xs 2.1 (33B) runs on device, and the earlier Laguna XS.2 is free for local use under Apache 2.0, with preview terminal and agent surfaces. Government options include air gapped operation, a hardened operating system and IL5 deployability.

What is public

Poolside publishes its deployment models and the government offer of on premises and air gapped inference with no per token fees. It also publishes the open weight Laguna xs 2.1 (33B) and Laguna s 2.1 (118B) models, available per token through OpenRouter and Vercel AI Gateway. Enterprise and government contract pricing, minimums and Forward Deployed Research Engineer fees are not published.

Billing mechanics

Enterprise is a custom contract covering software, deployment, and Forward Deployed Research Engineer support, with infrastructure either provided or customer owned. Bedrock is pay as you go per token under AWS. The open weight model is free.

Cost watchouts

The real cost of an enterprise deployment includes infrastructure, whether a Poolside provisioned rack, a cloud VPC, or customer NVIDIA hardware, plus the Forward Deployed Research Engineer engagement. Bedrock usage bills per token and scales with developer activity. Air gapped and government deployments add hardware and compliance overhead.

Variable cost rationale

Cost depends on the path. An enterprise deployment on committed or customer owned infrastructure behaves largely as a fixed cost, since inference runs on hardware the customer already pays for, and the government offer carries no per token fees. Access through Amazon Bedrock, OpenRouter or Vercel AI Gateway bills per token with no fixed seat, so cost there grows with developer activity, and no cap is published. The open weight models cost only the hardware they run on.

Additional watchouts

There is no public self serve price, and prices come only from a sales conversation. Total cost includes infrastructure and services, not just software. Government and air gapped deployments carry additional hardware and compliance overhead. The free open weight model is not the same as the governed enterprise platform.

Overage / add-ons

Enterprise contracts are custom, so overage terms are negotiated. Amazon Bedrock access bills per token with no fixed seat, so cost scales directly with usage.

Sales call required

Yes, required for paid access

Free / trial

Free developer access to the hosted Poolside Platform, a no sign up chat at chat.poolside.ai, and free open weight Laguna xs 2.1 and s 2.1 models, with xs 2.1 able to run on device. No trial of the enterprise platform.

Lowest paid plan

Not published for the platform. Per token access to Poolside models runs through Amazon Bedrock, OpenRouter and Vercel AI Gateway.

Commercial notes

Poolside is priced as a high touch enterprise platform, not a self serve tool, aimed at large organizations and the public sector that need models and agents inside their own boundary. Value concentrates where sovereignty, air gapped operation and joint delivery matter. The open weight models and per token use in Bedrock are lower cost entry points, without the governed platform around them.

Key ambiguities

No list price is public for the enterprise platform. Cost depends on deployment shape, developer count, hardware and the Forward Deployed Research Engineer engagement. Bedrock per token rates and any minimums are set through AWS. The boundary between free open weight use and paid platform capabilities is set by which components a team runs.

Cancellation / refund

Enterprise agreements are custom annual or multi year contracts negotiated directly. Bedrock usage is pay as you go under AWS terms, and the open weight Laguna models carry no contract.

Support SLA / resale

Enterprise deployments include Forward Deployed Research Engineer support. Poolside models are also offered per token through Amazon Bedrock, OpenRouter and Vercel AI Gateway.

Missing data

All enterprise list pricing, minimums, and Forward Deployed Research Engineer engagement costs are undisclosed. Bedrock per token rates are set through AWS.

Agentic Index verified 2026-10-25

Alternatives to Poolside

The closest documented capability profiles to Poolside among coding agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.

  • Ellipsis10.5 / 14A lighter documented profile than Poolside
  • OpenCode10.5 / 14A lighter documented profile than Poolside
  • Tabnine11.5 / 14Fuller documented coverage on Knowledge Grounding & RAG
  • Augment Code12.0 / 14Fuller documented coverage on Knowledge Grounding & RAG and Prebuilt Agents, Templates & Packs
  • Charm10.0 / 14A lighter documented profile than Poolside
  • CodeRabbit12.0 / 14Fuller documented coverage on Knowledge Grounding & RAG and Memory & State Persistence

Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded

Head to head

Contact us

Found a vendor we missed? Have feedback on the index? We'd love to hear from you.