$ buildwith diff serena sourcegraph

Serena vs Sourcegraph

Both are in Context & Indexing, where we rank Serena #2 and Sourcegraph #3. Everything below comes from each tool's own pricing and docs pages, with the date we last checked them. How we rank.

pick Serena if your coding agent needs to find a symbol, see who references it, and edit that symbol, instead of grepping and rewriting whole files.

pick Sourcegraph if your team already has Sourcegraph, or will, and you want coding agents to search across repositories and get file ranges back instead of reading the tree themselves.

Serena

#2 · Free / OSS

Serena is an MCP server that gives a coding agent symbol-level retrieval, editing, refactoring, and debugging, closer to an IDE than to line-based search. It does not run the model. Your client (Claude Code, Codex, OpenCode, Gemini CLI, Cursor, a JetBrains assistant, Claude Desktop, or another MCP client) calls Serena's tools. The default backend is free language servers. A paid JetBrains plugin, with a free trial, is the other backend. The README says not to install Serena from an MCP or plugin marketplace, because those commands are outdated. The supported install is uv, then uv tool install -p 3.13 serena-agent, then serena init.

for Developers who already have a coding agent and want it to navigate and edit a large or multi-language repo by symbol. The README's client list covers terminal agents, IDE assistants, and desktop or web MCP clients. You bring the model and the client. Serena is the tool server.

use this if your coding agent needs to find a symbol, see who references it, and edit that symbol, instead of grepping and rewriting whole files.

pricing

  • Language servers Free

    uv tool install -p 3.13 serena-agent, then serena init. This is the default backend. The application is GPL-3.0-or-later. SolidLSP, the language-server client library in the same repo, stays MIT. The README says a distribution that combines both, including the serena-agent package, is as a whole under the GPL.

  • JetBrains plugin Paid, free trial

    Optional backend. The README and the plugin docs call it a paid plugin with a free trial, and say purchases support Serena development. The plugin docs page does not list a price. You still run the Serena MCP server and connect your own client. The plugin is not a chat UI.

features

  • ›Retrieval over language servers: find symbol, a file's symbol overview, find referencing symbols, find declaration, diagnostics. Find implementations is only available for some languages. Search in project dependencies and type hierarchy are marked JetBrains-only
  • ›Symbolic edits on the free backend: replace symbol body, insert before or after a symbol, and safe delete. The README describes these as less error-prone than search-and-replace over file text. Rename of symbols works on language servers. Rename of files and directories, move, and inline are JetBrains-only
  • ›The language-server backend is the default and is described as supporting over 40 languages, including Python, TypeScript, JavaScript, Rust, Go, Java, C#, C and C++, Ruby, PHP, and others listed in the README. Some languages need extra dependencies
  • ›The JetBrains plugin adds dependency indexing, interactive debugging (breakpoints, variables, expressions, execution control), and one IDE process shared by many agent sessions. The docs say it is a backend for the MCP server, not a chat UI inside the IDE
  • ›A memory store for notes that can be shared across sessions, and YAML configuration at global, launch, project, and client-context levels. Inside Claude Code or Codex, the README says the basic file, search, and shell tools are typically disabled because the harness already has them
  • ›v2 adds a REPL-based agent interface. The README points at the docs for how to turn it on

strengths

  • ›On 2026-11-11 the GitHub API reported 31,273 stars and 2,136 forks. The repository was created 2025-03-23. GitHub's primary language is Python
  • ›Latest GitHub release on that date was v2.1.0, published 2026-10-19. The release notes say 'See change log' and do not list the changes themselves. PyPI serena-agent 2.1.0 was uploaded the same day and requires Python >=3.11 and <3.15
  • ›No embedding model and no vector index. Symbol lookup goes through a language server, or through a JetBrains IDE if you use that plugin, so a search does not add an embedding-API bill
  • ›The README's retrieval table is explicit about what the free backend cannot do, which makes the gap between the two backends checkable

limits

  • ›The Serena application from v2 onward is GPL-3.0-or-later. The LICENSE file says this is not retroactive: releases up to and including v1.7.0 stay MIT. A combined distribution such as the serena-agent package is under the GPL as a whole
  • ›Find declaration generally does not work for declarations in external dependencies. Find implementations depends on the language server and is missing for some languages. Dependency search, type hierarchy, move, and inline require the paid JetBrains plugin
  • ›The README calls the JetBrains plugin paid, with a free trial, and does not list a price. It also says Rider and CLion are unsupported
  • ›Serena does not index documents, meeting notes, or embeddings, and it does not keep a derived index fresh when files change. It answers the project that is open, through the language server or the IDE
  • ›The README's efficiency claims come from an evaluation prompt the project wrote and then summarized in the agents' own words. The page links a write-up. Those quotes are not an independent measurement of tokens saved

why #2

Ranked #2 in Context & Indexing. Serena is the symbol tool: find a symbol, find references, and replace a symbol body through language servers, with no embedding model described in the README. It had 31,273 GitHub stars on 2026-11-11. It ranks second because it does not keep an index of documents or code chunks fresh as sources change, and the free backend stops short of dependency search and several refactors. Sourcegraph ranks third: it searches across an organization's repositories, and its MCP server is an Enterprise plan. The JetBrains plugin that adds those is paid, and the README does not list the price. The scores are unmeasured placeholders and are not shown.

sources

open oraios.github.io ↗

Sourcegraph

#3 · Paid

Sourcegraph MCP gives coding agents a retrieval layer over the code indexed in a Sourcegraph instance: keyword and semantic search, file reads, navigation, history, and Deep Search. Code Finder is the tool built for this job. You give it a task, it runs its own search loop, and it returns a short summary plus the matching file paths and line ranges, so the agent reads that instead of opening files until it finds the right ones. The page says go-to-definition and find-references use precise code indexing (SCIP), an open standard.

for An engineering team that wants one place for humans and agents to search a large, multi-repository codebase. The pricing page describes a single Enterprise plan for that, with search and navigation, Deep Search, and MCP access, deployed as single-tenant cloud or self-hosted.

use this if your team already has Sourcegraph, or will, and you want coding agents to search across repositories and get file ranges back instead of reading the tree themselves.

pricing

  • Enterprise From $16,000/year

    The pricing page shows one plan, starting at $16,000 as the minimum annual contract. It includes credits for AI features that scale with team size. The summary does not say how many credits that is. Credits are per user, pooled across the org, and do not expire monthly. Purchased credit buckets roll over on renewal. Volume credit buckets are an add-on. The plan lists search and navigation, Deep Search, Batch Changes, Insights, Monitoring, the full MCP server, API, and CLI, single-tenant cloud and self-hosted, and 24×5 support.

features

  • ›The docs open with 'Supported on Enterprise plans.' The default endpoint, /.api/mcp, includes code_finder, keyword_search, read_file, list_files, list_repos, commit_search, diff_search, deepsearch_read, and evaluator. nls_search is a fallback on that endpoint when code_finder is unavailable or disabled
  • ›Go-to-definition, find-references, creating a Deep Search conversation, compare_revisions, and list_refs are on /.api/mcp/all, not the default endpoint. /.api/mcp/deepsearch is Deep Search only
  • ›read_file can take a line range and a revision. Files over 128KB return the first 200 lines and a truncation notice. list_files stops at 1,000 entries. find_references defaults to 10 results. The docs say every tool limits results so a call does not fill the context window
  • ›Code Finder takes a task and an optional revision. It searches one repository you name, runs synchronously, and returns paths and line ranges with a short explanation. Usage is metered against the instance entitlement. When the quota is used up, the tool returns an error
  • ›OAuth or a Sourcegraph access token. Users need the MCP#ACCESS permission, which the built-in User role has unless an admin removes it. Repository permissions still apply. Admins can set mcp.enabled to false or disable individual tools, including code_finder
  • ›The docs name Claude Code, Codex, Cursor, Copilot, OpenCode, and Amp as clients. A client that fails OAuth with invalid_scope should request only the mcp scope

strengths

  • ›On 2026-11-11 the GitHub API reported 10,285 stars and 1,376 forks on sourcegraph/sourcegraph-public-snapshot. The repository was created 2015-08-24. Primary language is Go. It is archived. The last push was 2024-09-02
  • ›The README says development moved to a private monorepo and this repository is a public copy of sourcegraph/sourcegraph from just before that move. It points at one commit as the last change made under Apache-2.0. Stars on this repo are for that snapshot
  • ›The self-hosted releases index lists 8.1.4873, published 2026-11-11, as the latest patch of 8.1. That page describes an executor host-kernel fix for CVE-2026-99999. It is not a commit in the archived snapshot: https://sourcegraph.com/changelog/releases/8.1.4873
  • ›A July 23, 2026 Sourcegraph post says that, on a file-finding suite they assembled, Code Finder finished more than twice as fast as an agent using local search and cost up to 40% less than an agent calling Sourcegraph's own MCP tools, at comparable quality. The post says the chart is relative to Code Finder and does not list the tasks or absolute token counts: https://sourcegraph.com/blog/code-finder-fast-code-search-for-agents

limits

  • ›LICENSE.enterprise says the software may be used in production only with a valid Sourcegraph Enterprise subscription for the correct number of seats, under the Enterprise terms or another agreement. You may copy and modify it for development and testing without a subscription
  • ›Beyond that, the same license forbids copying, merging, publishing, distributing, sublicensing, or selling the software. Sourcegraph keeps title to modifications and patches, and those may only be used with a valid subscription for the correct number of seats

why #3

Ranked #3 in Context & Indexing. Sourcegraph is the long-running code search product in this list: an agent asks an indexed copy of the company's repositories and gets paths and line ranges back, including through Code Finder. The MCP docs say that server is supported on Enterprise plans. It ranks below CocoIndex and Serena because those two run locally without that plan. It ranks above Repomix because a pack still drops a repository into the prompt, while this server is built to return a slice. The scores are unmeasured placeholders and are not shown.

sources

open sourcegraph.com ↗
sponsor this spot →