# Glean — Enterprise AI platform for building, governing and running agents on permission-aware company context.

> Source: The Agents Index — https://theagentsindex.com/glean (structured, researched, re-verified)
> Facts last verified: 2026-09-02

Glean is an enterprise AI platform that indexes a company's applications and lets teams build, orchestrate and govern permission-aware AI agents on that context. It pairs enterprise search across connected work apps with a no-code builder for agents that read and act in those systems.

| Fact | Value |
| --- | --- |
| Website | https://www.glean.com |
| Free tier | No |

No free or self-serve tier is published. Both pricing models require a per-user licence plus either an upfront Model Hub Usage commit (Core Suite) or a base FlexCredit pool (Enterprise Flex); the only entry point on the site is 'Get a demo'.

## What it does

**Writes code** · Yes — Code Writer proposes code changes and opens draft pull requests in GitHub, callable from Glean, agents or Slack.

> Code Writer lets you use Glean Assistant and Glean Agents to propose code changes and open draft pull requests in GitHub.
> — https://docs.glean.com/administration/assistant/features/code-writer · Code Writer, opening paragraph

**Debugs and fixes** · Yes — Vendor names bug fixes as a target task; the Resolve Jira ticket agent turns an issue into a review-ready PR.

> It helps you complete coding tasks such as bug fixes, refactors, and updates without changing your existing GitHub review and deployment processes.
> — https://docs.glean.com/administration/assistant/features/code-writer · Code Writer, opening paragraph, second sentence

**Writes tests** · Partly — Test changes appear in the vendor's own agent example output; no dedicated test-generation feature is documented.

> Implements recurring billing API and background processing according to the documented design, including schema, endpoints, worker, and tests
> — https://www.glean.com/agent-library/spec-to-implementation-pr · Example output block, delivery summary

**Reviews code** · Yes — The pull request review agent fetches a PR diff, checks it against style guides and posts comments back to GitHub.

> The pull request review agent automates the end-to-end PR review process, ensuring code quality, consistency, and up-to-date documentation.
> — https://www.glean.com/agent-library/pull-request-review · Overview section, first sentence

**Whole-codebase work** · Partly — Code Writer is scoped to a small targeted change in one configured repository and branch, not a repository-wide migration.

> Plans a small, targeted change based on user instructions and context.
> — https://docs.glean.com/administration/assistant/features/code-writer · Where Code Writer can be used, numbered step 2

**Ships it** · No — It stops at a draft pull request; review and merge stay in the customer's source control.

> Review and merge decisions always stay in GitHub.
> — https://docs.glean.com/administration/assistant/features/code-writer · Where Code Writer can be used, note callout

**Done-for-you service** · No — Glean sells licensed software; it manages the infrastructure and application but customers build and run their own agents.

> Glean is responsible for infrastructure and application management, including upgrades, patching, and monitoring.
> — https://docs.glean.com/get-started/prepare/about-deployment · Glean deployment models, list of properties that hold regardless of deployment model

## How much it does unattended

**Runs autonomously** · Yes — Autonomous agents plan their own approach from plain-language instructions, and time-based triggers run them unattended.

> Autonomous agents interpret your plain-language instructions to determine the best approach to solve complex enterprise use cases .
> — https://www.glean.com/ai-agents/agent-builder · AI agent builder - Autonomous agents section

**Multi-agent** · Yes — Orchestration activates specialist agents in sequence on one multi-step task and shares context between them.

> Orchestration connects specialized agents to complete multi-step tasks, activating each one at the right time and sharing context seamlessly along the way.
> — https://www.glean.com/ai-agents/agent-orchestration · Coordinate multi-agent workflows section

**Agent permissions** · Partly — Write actions require confirmation and are checked before execution; source-system permissions are re-checked on every request, but read work proceeds unattended.

> Enforce source-system permissions on every read and write; an agent should not automatically access everything the user can.
> — https://www.glean.com/platform/security · AI security control points, item 02 Data permissions

## Which models it runs on

**Claude** · Yes — Anthropic models are offered through Google Vertex AI or Amazon Bedrock, or directly with your own Anthropic key.

> Anthropic (Claude) models are accessible through Google Vertex AI or Amazon Bedrock. With Customer Key, you can also connect directly to Anthropic using your own Anthropic API key
> — https://docs.glean.com/administration/llms · Availability by hosting environment and provider, bullet list under the table

**GPT** · Yes — OpenAI models are listed in the Model Hub text-model table, via Azure or OpenAI directly.

> The Model Hub offers a curated set of leading models from providers like OpenAI, Google, Anthropic, and Amazon.
> — https://docs.glean.com/administration/llms · Supported LLMs, opening paragraph

**Open models** · Yes — Open-weight models are a named tier in the rate card, served through Fireworks or Baseten.

> Open (via Fireworks or Baseten)
> — https://docs.glean.com/glean-enterprise-flex-pricing · Model Tiers table, Standard tier, Model Family cell

**Model choice** · Yes — Admins choose which of 40+ models are available and to whom; auto routing can pick per task instead.

> AI usage controls let admins turn models on or off, control model access by user or department, and set usage limits to manage spend by user, agent, or department.
> — https://www.glean.com/platform/model-hub · Governance - Model choice on your terms section

## Where you use it

**In your editor** · Yes — A remote MCP server puts Glean inside Cursor, VS Code, Windsurf, JetBrains AI Assistant and Claude Desktop.

> Run Glean in MCP-enabled IDEs and apps like Cursor, VS Code, Windsurf, and Claude Desktop.
> — https://www.glean.com/platform/api · Build your way with open APIs, Remote MCP servers card

**On the command line** · Partly — No Glean CLI of its own; a plug-in exposes Glean tools inside terminal coding agents such as Claude Code, Codex, Gemini CLI and OpenCode.

> The Glean plug-in gives Cursor, Claude Code, and Codex users access to Glean Skills and tools.
> — https://docs.glean.com/administration/platform/mcp/glean-plugin · Glean plug-in for coding hosts, opening paragraph

**In your pipeline** · Partly — Agents act on pull requests through the GitHub API, writing comments, descriptions and patches, but Glean runs no CI job of its own and respects existing branch protections.

> Using the GitHub API, the agent adds comments directly to the PR.
> — https://www.glean.com/agent-library/pull-request-review · Agent workflow, Step 6: Post comments to GitHub

**In a browser** · Yes — Browser app, sidebar and companion, plus desktop and mobile apps, all included in the seat fee.

> Browser (App, Companion, Sidebar)
> — https://docs.glean.com/glean-enterprise-flex-pricing · Enterprise Flex Seats table, Glean Assistant / Fast Mode Queries row, Access Surfaces cell

## Whose machine it runs on

**Self-hosted** · Partly — Customer Hosted runs Glean inside your own AWS or GCP account, but as a Glean-operated managed service you may not deploy or patch yourself.

> Customer Hosted is equivalent to a hosted-SaaS model, where Glean still has minimal access to operate it like a SaaS service.
> — https://docs.glean.com/get-started/prepare/about-deployment · Customer Hosted section, 'Not a traditional self-hosted model' callout

**Open source** · No — Closed, vendor-operated system: even in the customer's own cloud, altering or patching Glean services is unsupported.

> In the Customer Hosted model, Glean doesn't support manually deploying or patching the Glean services, or altering any part of the Glean architecture.
> — https://docs.glean.com/get-started/prepare/about-deployment · Customer Hosted section, warning callout

## What it costs to run

**How it meters** · Yes — Per-user monthly seat, plus metered consumption on top: pooled FlexCredits under Enterprise Flex, or per-million-token Model Hub Usage under Core Suite.

> With Enterprise Flex you get the simple budgeting of a per-user license, combined with a pooled allowance of pay-per-use credits when your organization extensively uses advanced Al features.
> — https://docs.glean.com/glean-enterprise-flex-pricing · Glean Enterprise Flex, opening paragraph

**Free tier** · No — Licensed per user per month with an upfront usage commit; every call to action on the site is a demo request, and no self-serve or free tier is published.

> Licensed on a per-user, per-month basis, Glean Core Suite includes:
> — https://docs.glean.com/glean-core-suite-pricing · Glean Core Suite, paragraph introducing the inclusions table

**API access** · Yes — Search, Chat, Agents, Indexing and Tools APIs plus a Web SDK; Search API is in the seat fee, Chat and Agents APIs draw metered usage.

> Search API (included in seat)
> — https://docs.glean.com/glean-core-suite-pricing · Glean Core Suite table, Glean Developer Tools / Client APIs row, Capabilities cell

**MCP server** · Yes — A remote Glean MCP server exposes Glean tools and agents to other AI hosts; Glean can also consume external MCP servers.

> Yes. Teams can automate work with native actions, create custom actions using OpenAPI and MCP, and use Glean in MCP-enabled IDEs and apps.
> — https://www.glean.com/platform/api · FAQs, 'Does Glean support custom actions and MCP-enabled workflows?'

**Bring your own key** · Yes — Customer Key lets you use your own provider keys, and credits are discounted for doing so; Glean's Universal Model Key is the alternative.

> You can bring your own keys for providers or use Glean’s Universal Model Key to access pre‑procured models with guardrails.
> — https://docs.glean.com/administration/llms · Supported LLMs, opening paragraph

## Buying it for a team

**A company can buy it** · Yes — Sold as an organisation-wide licence with per-user seats and site-wide annual add-ons; no individual purchase path exists.

> Licensed on a per-user, per-month basis, Enterprise Flex Seats are designed to be deployed to every employee in your organization
> — https://docs.glean.com/glean-enterprise-flex-pricing · Enterprise Flex Seats, opening paragraph

**Seat model** · Yes — Per-user, per-month seats intended for every employee; the published tables state no seat floor or ceiling and no seat price.

> Licensed on a per-user, per-month basis, Enterprise Flex Seats are designed to be deployed to every employee in your organization
> — https://docs.glean.com/glean-enterprise-flex-pricing · Enterprise Flex Seats, opening paragraph

**Pooled budget** · Yes — FlexCredits are pooled organisation-wide, with limits then set per department, user or agent.

> FlexCredits are shared and pooled at the organizational level, and make it simple for users to access advanced features and additional consumption beyond included seat capabilities.
> — https://docs.glean.com/glean-enterprise-flex-pricing · FlexCredits section, first paragraph

**Admin controls** · Yes — Admins gate model access, agent sharing scope and monthly spend by department, user or agent, and can disable premium models entirely.

> Start with a company-wide monthly limit, then tailor it by department, user, or agent. Set alert timing and decide what happens when a limit is reached.
> — https://www.glean.com/platform/cost-controls · Usage limits - Set limits that fit your business section

**Audit log** · Yes — Admin audit logs cover configuration and administrative actions with CSV export; default retention is 30 days and end-user activity sits in separate event logs.

> Glean's Admin Audit Logs provide comprehensive visibility into administrative actions performed within your Glean instance.
> — https://docs.glean.com/administration/management/audit-logs/admin-audit-logs · Audit Logs, opening paragraph

**Single sign-on** · Yes — OIDC and SAML, mandatory before setup; Okta, Entra ID, OneLogin and Google are named, with OIDC recommended.

> Glean SSO utilizes standard authentication protocols such as OpenID Connect (OIDC) and Security Assertion Markup Language (SAML) to establish a secure communication channel between Glean and an organization's identity provider (IdP).
> — https://docs.glean.com/administration/identity/sso/about · Understanding Glean SSO, first paragraph

## What happens to your code

**Opt out of training** · Yes — Zero LLM data retention is in the seat fee, and the Universal Model Key is stated not to train on your data.

> Get ZDR-compliant access to leading open and frontier models across providers. Your data isn’t used for model training, with consistent security across open and proprietary models.
> — https://www.glean.com/platform/model-hub · Glean Universal Model Key - One secure key to access leading models section

**Data residency** · Yes — Regional residency on Glean-hosted single tenants; Customer Hosted keeps data inside your own AWS or GCP account, with no GovCloud regions.

> Full data residency guarantees - data doesn't leave your organizational boundaries.
> — https://docs.glean.com/get-started/prepare/about-deployment · Customer Hosted, Advantages list, first bullet

**Getting out** · Partly — Audit logs, usage tables, org charts and agent definitions export to CSV, and Glean can stream logs to storage you own; nothing published says whether unused FlexCredits expire.

> The Admin console provides on-demand CSV export of audit log data for external analysis, compliance reporting, and long-term record keeping.
> — https://docs.glean.com/administration/management/audit-logs/admin-audit-logs · Export and Reporting section, first paragraph

**Certifications** · Yes — SOC 2 Type 2, ISO 27001:2022, ISO/IEC 42001:2023, HIPAA and GDPR, with reports and certificates available on request; the marketing site adds TX-RAMP Level 2.

> Glean SOC 2 Type 2 Report
> — https://trust.glean.com · Compliance list (SOC 2, ISO 27001:2022, ISO/IEC 42001:2023, HIPAA, GDPR) and Resources, Reports & Certifications

## Provenance

Every fact above comes from the vendor. Nothing here is independently corroborated yet.

## Coverage elsewhere

Pages about this product that the vendor does not control. The label states how independent each one is.

| Source | Kind | Read |
| --- | --- | --- |
| en.wikipedia.org | Platform record | 2026-08-23 |
| fortune.com | Independent source | 2026-08-23 |
| vendr.com | Independent source | 2026-08-23 |
| g2.com | Review platform | 2026-08-23 |

## What changed

- 2026-09-02 — Capabilities · Commercial terms · Free tier
- 2026-08-31 — Capabilities · Commercial terms · Free tier
- 2026-08-23 — One-liner · Summary

## Correcting this record

Anything marked "Not established" is a question we have not answered — it is not a No. If you represent Glean, or anything here is wrong or out of date, you can supply it with a source: the operations this site accepts from an agent are listed at https://theagentsindex.com/.well-known/agents.json — that catalogue needs no key to read, and each entry states its own auth.

Supplying evidence is free. Nothing that can be bought here changes what a field says, whether a gap is closed, or how this record is scored.