Back to vendors
S

Sourcegraph

Also known as: Cody, SCIP

Visit site
Entry priceEnterprise from $16K a year (minimum annual contract, AI credits included). Agentic Batch Changes is metered per user per repository run, and its model use draws on credits.Full pricing detail

Code intelligence platform whose code graph indexes entire organizations for exhaustive search, Deep Search answers with citations, and Batch Changes across many repositories. An MCP server feeds that code graph to third party coding agents as context.

Sourcegraph is a code intelligence platform built to help both engineers and AI agents understand, oversee, and safely change very large, complex codebases. Major engineering organizations use its code search, which searches across every repository, branch, and code host with exact, exhaustive results. A code graph that maps the relationships between symbols, references, and definitions throughout a codebase powers that search.

That code graph anchors a wider set of capabilities. Deep Search lets a developer ask a complex question in natural language and get a grounded answer with citations from an agent that explores the repositories on its own. Batch Changes rolls out the same fix, refactor, or migration across many repositories at once with control at scale. And tools for code insights, monitoring, and living documentation track how a codebase evolves over time and flag risky changes as they happen.

The code graph also serves as a context layer for AI coding agents. An agent working on one task usually sees only fragments of an enterprise codebase, so it can miss changes or introduce inconsistencies. Sourcegraph indexes all of an organization's repositories and, through an MCP server, feeds agents complete, precise context so they produce better results with fewer retries and lower inference cost.

Sourcegraph also ships its own AI coding tools. Cody is its assistant for writing, fixing, and understanding code inside IDEs, drawing on full codebase context and letting developers choose among frontier models from Anthropic, OpenAI, and Google. Cody is focused on enterprises. Agentic Batch Changes, now generally available, takes a plain language change, scopes it across the indexed codebase, and routes each repository to a deterministic script or a delegated coding agent, tracking every pull request through to merge. Amp, the agentic coding tool that began at Sourcegraph, is now a separate company.

Built for the largest monorepo and multi-repository architectures, Sourcegraph supports cloud, self-hosted, and air-gapped deployments and keeps LLM inference data out of retention. It holds SOC 2 and ISO 27001 compliance and offers single sign-on and role-based access.

Vendor details

Canonical URL

https://sourcegraph.com/

Category

Agent infrastructure

Funding status

Independent. Founded 2013 by Quinn Slack and Beyang Liu. Raised over $200M, most recently a $125M Series D led by Andreessen Horowitz in July 2021 at a $2.625B valuation, with Craft, Redpoint, Sequoia and Goldcrest also on the board. In December 2025 the company split in two: Dan Adler became CEO of Sourcegraph, focused entirely on code search and code understanding, while Slack and Liu founded Amp Inc. as a separate company for frontier coding agents, remaining on Sourcegraph's board.

Company status

independent

Use cases & customers

Target customers

enterprisesdevelopers

Deployment options

Sourcegraph CloudSelf-hostedAir-gappedCustomer-chosen model endpoints (Azure OpenAI, AWS Bedrock, OpenAI-compatible)

Integrations

An MCP server exposes the code graph so any compatible third-party agent can request precise repository context. Cody Enterprise integrates with VS Code, JetBrains, Visual Studio and a CLI, retrieving context from up to ten repositories at once. Code host integrations cover every major platform for indexing, a browser extension adds search and navigation on code host pages, and public APIs drive search and Batch Changes programmatically. Cody supports Anthropic, OpenAI and Google models and customer-chosen endpoints including Azure OpenAI, AWS Bedrock and OpenAI-compatible gateways.

In practice

Your AI agents keep making inconsistent changes because each one only sees a slice of a sprawling enterprise codebase. Sourcegraph indexes every repository and feeds agents complete code-graph context through its MCP server, so their output is reliable.

You need to apply the same security fix across hundreds of repositories without missing any. Sourcegraph's Batch Changes rolls the change out everywhere at once, with control to review and track it at scale.

A new engineer needs to understand how a function is used across the whole system. Sourcegraph's code search and Deep Search return exact references and a natural-language answer with citations, instead of grepping through hundreds of files.

Agentic Index coverage score

11.5 / 14 capabilities · 82%

Integrations & Tool Calling Full

Changesets go out to each code host through Agentic Batch Changes, which runs CI across GitHub, GitLab and Bitbucket and tracks each pull request through to merge, and the platform indexes all major code hosts. The MCP server works the other way, exposing Sourcegraph's own code graph to agents such as Claude Code, Cursor, Codex and Amp.

Sourcesourcegraph.com/agentic-batch-changesread 2026-09-29

Workflow Orchestration Full

Agentic Batch Changes, now generally available, runs a coordinator agent that takes a plain-language change and scopes it across the indexed codebase with Deep Search. It splits the work by code ownership and routes each repository to a deterministic script or a delegated coding agent, in isolated containers running in parallel, then publishes changesets, reads CI logs and patches failures until CI is green.

Sourcesourcegraph.com/agentic-batch-changesread 2026-09-29

Knowledge Grounding & RAG Full

The code graph indexes every repository, branch and code host across an organization, mapping relationships between symbols, references and definitions for exhaustive exact search at monorepo and multi repository scale. Deep Search runs an agent that explores repositories autonomously and returns grounded answers with citations, Cody Enterprise retrieves relevant code from up to ten repositories simultaneously, and an MCP server feeds that complete indexed context to third party agents.

Sourcesourcegraph.com and sourcegraph.com/docsread 2026-08-30

Human Oversight & Guardrails Full

Agentic Batch Changes researches, plans and revises freely without publishing anything. The first run usually takes an explicit yes. Publishing and rollout can each wait on a person's reply unless they were authorized up front, and steps that use secrets wait for approval. Teams validate a change on a few repositories before rolling it out.

Sourcesourcegraph.com/docs/agentic-batch-changes/configurationread 2026-10-25

Security, Identity & Governance Full

Sourcegraph states SOC 2 Type II and ISO 27001 compliance and offers enterprise authentication with SSO through SAML, OpenID Connect and OAuth, SCIM provisioning and lifecycle management, and RBAC. Authentication can be configured through SAML, OAuth, HTTP proxy and OpenID Connect, annual third-party penetration tests are run, and LLM inference data has zero retention.

Sourcesourcegraph.comread 2026-09-29

Observability & Auditability Full

The Agentic Batch Changes console records the coordinator's run step by step, covering scoping, container launch per repository, changeset publication per code host and each CI failure read and patched. It shows per-repository execution status, per-changeset PR tracking in the web UI and coverage tracking of which repositories have landed, and Batch Changes execution keeps executor and pull request sync state. No retention period or export for run records is published.

Sourcesourcegraph.com/agentic-batch-changesread 2026-09-29

Memory & State Persistence Partial

Agentic Batch Changes keeps run state across a migration, including which repositories are in scope, which changesets have landed and pull request sync, and follows customizable skills and AGENTS.md set per user, org or globally. The skills are instructions the customer writes and the code graph is a search index, so what persists is run state, with no stated scope, lifetime or review.

Sourcesourcegraph.com/agentic-batch-changesread 2026-09-29

Deployment & Data Residency Full

Deployment spans Sourcegraph Cloud, customer self hosted instances and fully air gapped environments for the largest monorepo and multi repository architectures. LLM inference data is kept out of retention, and Cody supports cloud hosted or self hosted model endpoints including Azure OpenAI, AWS Bedrock and OpenAI compatible gateways.

Sourcesourcegraph.com and sourcegraph.com/docs/admin/deployread 2026-08-30

Prebuilt Agents, Templates & Packs Partial

Batch Changes are defined by reusable declarative specification files that can be templated, versioned and shared for recurring cross repository migrations, with published example specs, and saved searches and code monitors are reusable configuration. There is no catalog of installable prebuilt agents, skills or packs.

Sourcesourcegraph.com/docs/batch-changes and sourcegraph.comread 2026-08-30

Triggers & Channel Coverage Full

Code Monitoring alerts agents and teams the moment code changes, and Agentic Batch Changes uses changeset hooks for CI so the agent reacts to CI results and iterates without being prompted. Both start work when an event occurs. The web app, IDE extensions, CLI and MCP server are used on demand.

Sourcesourcegraph.comread 2026-09-29

Model Flexibility & Routing Full

Cody's supported models include chat and prompt models from Anthropic (Claude Opus and Sonnet 5 line, Haiku 4.5), Google (Gemini 3.x Flash and Pro) and OpenAI (GPT-6), which site admins configure through modelConfiguration and users select per use case, alongside customer chosen endpoints on Azure OpenAI, AWS Bedrock and OpenAI compatible gateways. Cody is no longer listed on the pricing page, though its model reference is current.

Sourcesourcegraph.com/docs/cody/capabilities/supported-modelsread 2026-09-29

APIs, SDKs & MCP Extensibility Full

An MCP server is a shipped product exposing the code graph to third party agents, alongside public APIs that drive code search and Batch Changes programmatically, a CLI, IDE extensions for VS Code, JetBrains and Visual Studio, and a browser extension. The SCIP Code Intelligence Protocol is fully open source, though the Sourcegraph and Cody source code moved to private repositories, with only a public snapshot remaining.

Sourcesourcegraph.com, sourcegraph.com/docs and github.com/sourcegraph/scipread 2026-08-30

Testing, Debugging & Optimization Partial

Complete code graph context, Sourcegraph says, makes third party agents produce better results with fewer retries and lower inference cost. Code Insights track code health metrics over time, and Batch Changes previews validate a change set before it is applied. There is no customer facing harness for testing, evaluating or regression testing agent behavior.

Sourcesourcegraph.com and sourcegraph.com/docsread 2026-08-30

Browser & Computer Use Not documented

Sourcegraph operates on indexed repositories through its web application, IDE extensions, CLI and MCP server. A browser extension adds code search and navigation to code host pages, but it is a UI overlay for the user, not the agent operating software, and there is no browser control or computer use capability.

Sourcesourcegraph.comread 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

·MCP / tool calling / APIVerified

Connector support for Sourcegraph agents now extends to personal connectors, which each user adds from their own settings next to the shared ones admins set up. Agentic Batch Changes and the coding agents it runs can then call MCP servers such as Jira, Linear, Confluence or a CI provider for context. Personal connectors are allowed for every user by default, and admins can switch them off by removing a single permission.

Bears on: MCP / tool calling / API

View source
·Workflow orchestrationVerified

Agentic Batch Changes no longer holds the conversation open while its workspaces run. The agent starts the runs and ends its turn, so users can ask how a migration is going while execution continues in the background. It then resumes by itself to review results, and can inspect a failed workspace while others are still running before reporting on the finished work.

Bears on: Workflow orchestration

View source
·Security / enterpriseVerified

Batch changes run by the Agentic Batch Changes agent are now applied and published as the user acting on them, and workspace execution jobs run as that user too. The same update adds collaborator grants for an agent, which can be issued and revoked through the API.

Bears on: Human approval / guardrails

View source
View all 13 Sourcegraph updates →Tracked since May 2026 · Verified from public vendor sources

Pricing

Enterprise from $16K a year (minimum annual contract, AI credits included). Agentic Batch Changes is metered per user per repository run, and its model use draws on credits.

Annual platform contract that scales with team size, with credits for AI features included per user and pooled across the organization. Agentic Batch Changes runs are metered per user per repository through an entitlement.

Included quota

Enterprise covers code search and navigation, Deep Search, Batch Changes, Insights and Monitoring, the full MCP server, API and CLI, code insights and advanced security at scale, with credits for AI features included per user. It deploys as single tenant cloud, self hosted, BYOC or air gapped, with SOC 2 and a guarantee of no training on customer code. Cody, where licensed, adds AI chat, autocomplete and inline edits with cross repository context (all org repos, 10+ at once), Context Filters and admin chosen LLMs (Claude Sonnet and Opus, GPT-4o, o1, Gemini).

What is public

Sourcegraph publishes a single Enterprise plan starting at $16K as a minimum annual contract that includes AI credits and scales with team size, covering code search and navigation, Deep Search, Batch Changes, Insights and Monitoring, the full MCP server, APIs and CLI, single tenant cloud or self hosted deployment and 24x5 support. Agentic Batch Changes runs are metered per user per repository. Cody has no listed price, and Amp became a separate company in December 2025.

Billing mechanics

Minimum annual contract from $16K, scaled by team size, with credits for AI features included per user, pooled across the organization, no monthly expiry and rollover of purchased buckets on renewal. Volume credit buckets are an add on, and premium support is optional. Agentic Batch Changes meters runs per user per repository, with model use drawing on credits.

Cost watchouts

AI features consume credits beyond the included allotment, large migrations through Agentic Batch Changes draw runs and credits, self hosted deployments add infrastructure and maintenance cost, and premium support is extra.

Variable cost rationale

The annual contract is fixed, from a $16K minimum that scales with team size. AI features draw on credits included per user and pooled across the organization. Agentic Batch Changes meters each run per user per repository, and its model use draws on the same credits, so heavy AI use or large migrations add variable cost. Credits do not expire monthly, volume credit buckets can be added, and purchased buckets roll over on renewal. The rate for extra credits and the price of a run are not published.

Additional watchouts

There is no self serve or small team plan, and the entry point is a $16K annual minimum through sales. The number of AI credits per user and what happens when the pool runs out are not published, and Sourcegraph lists no Cody price.

Overage / add-ons

Credits are pooled across the organization with no monthly expiry, purchased credit buckets roll over on renewal, and volume credit buckets can be added. Agentic Batch Changes model use draws on the same credits.

Sales call required

Yes, required for paid access

Free / trial

No free plan is listed, and no trial terms are published on the pricing page.

Lowest paid plan

Enterprise from a $16K minimum annual contract, about $1,333 a month

Commercial notes

Founded in 2013 in San Francisco by Stanford graduates Quinn Slack and Beyang Liu. Sourcegraph counts about 800k developers, indexes 50B+ lines of code, and counted Uber, Dropbox and Lyft among early customers. Its core is cross repository code graph context at enterprise monorepo scale. Amp was spun off into a separate company in December 2025, leaving Sourcegraph focused on code search and code understanding.

Key ambiguities

How the contract scales above the $16K annual minimum is negotiated. Whether Cody is still licensed under the Enterprise plan is not stated, since Sourcegraph lists no Cody price, and Cody Free and Pro have been discontinued.

Cancellation / refund

Enterprise is a minimum annual contract, and multi year terms bring discounts. Purchased credit buckets roll over on renewal.

Support SLA / resale

Enterprise includes 24x5 support with upgrade options, plus an optional customer success manager and optional premium support. Deployment runs single tenant, self hosted, BYOC or air gapped, with SOC 2, no training on customer code and admin LLM selection.

Missing data

The credit allotment per user, the rate for extra credits and the price per changeset for Agentic Batch Changes are not published.

Agentic Index verified 2026-10-25

Alternatives to Sourcegraph

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

  • Thread AI11.0 / 14A lighter documented profile than Sourcegraph
  • xpander.ai12.0 / 14Fuller documented coverage on Memory & State Persistence
  • Cartesia10.5 / 14A lighter documented profile than Sourcegraph
  • Kestra12.5 / 14Fuller documented coverage on Memory & State Persistence and Prebuilt Agents, Templates & Packs
  • Netlify10.5 / 14A lighter documented profile than Sourcegraph
  • Agno13.0 / 14Fuller documented coverage on Memory & State Persistence and Prebuilt Agents, Templates & Packs

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

Contact us

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