$ buildwith diff cocoindex serena

CocoIndex vs Serena

Both are in Context & Indexing, where we rank CocoIndex #1 and Serena #2. Everything below comes from each tool's own pricing and docs pages, with the date we last checked them. How we rank.

pick CocoIndex if you want a coding agent to search a repo by meaning and get back small chunks, or you want an index of code and documents that only reprocesses what changed.

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.

CocoIndex

#1 · Free / OSS

CocoIndex is an open-source Python framework that keeps code, documents, and meeting notes ready for agents by reprocessing only what changed. You declare the target in Python. The engine memoizes results when the inputs and the function code are unchanged, tracks which source items and which logic are affected, and runs independent work in parallel. Install the framework with pip install -U cocoindex. The same page describes CocoIndex Code Plus as a licensed code-search product, built on CocoIndex Plus, that searches indexed repositories and follows symbol references.

for People building agents and LLM apps that need a current view of code, documents, or meeting notes. The page's examples are a repo index for code-review and coding agents, a meeting-notes knowledge graph, and a repository wiki. A Claude skill on the same page is for writing the pipeline. CocoIndex Plus is the path the page points to for running at scale.

use this if you want a coding agent to search a repo by meaning and get back small chunks, or you want an index of code and documents that only reprocesses what changed.

pricing

  • Open source Free

    pip install cocoindex. One flow process, embedded LMDB state, a local target. The page says LMDB has one writer, and local storage and write throughput can limit how large a deployment gets. The same flow code runs on Plus with a different SDK package and state store. The comparison marks the GitHub connector, multi-node compute, and shared components as not included here.

  • CocoIndex Plus Quote

    pip install cocoindex-plus, plus a license key. Shared Postgres state on your cloud or your own servers, including Kubernetes and a Helm chart. The page does not list a dollar price. It says they answer with a deployment plan and a license. Multi-node compute, sharding, and dynamic sources are marked on request. The usage dashboard is marked in development. OpenTelemetry export is marked available.

features

  • ›cocoindex-code is an Apache-2.0 CLI (ccc) and a stdio MCP server. It parses files with Tree-sitter, tries to split them at function and class boundaries, and embeds the chunks. Chunks target about 1,000 characters, which the page calls about 300 tokens
  • ›The MCP search tool defaults to 5 results (limit 1 to 100). The page says the code in that result is at most about 1,500 tokens, plus file paths, line numbers, and scores. A whole-file read costs the length of the file, and that file is sent again on later turns until the client compacts the conversation
  • ›ccc search, which the skill runs, returns up to 10 results by default. --limit 5 matches the MCP default. offset, a path glob, and a language filter narrow the call. The MCP parameter names are limit, offset, paths, and languages
  • ›Install with pipx install 'cocoindex-code[full]' or uv tool install --upgrade 'cocoindex-code[full]', then ccc index in the repo. Claude Code: npx skills add cocoindex-io/cocoindex-code, or claude mcp add cocoindex-code -- ccc mcp. Codex: codex mcp add cocoindex-code -- ccc mcp. Other stdio clients start ccc mcp with the project as the working directory
  • ›The MCP search tool refreshes the index before each query by default. ccc index re-indexes changed files. With the local model, indexing cost is compute on your machine. With a cloud embedding provider, you pay that provider per token
  • ›The page says the saving depends on the repository and the task, and to measure it by running the same task with and without the search tool. Search does not change how many tokens the agent writes. Questions about callers and references need Serena or CocoIndex Code Plus (ccx), which is a separate self-hosted product

strengths

  • ›Apache-2.0. On 2026-11-11 the GitHub API reported 11,875 stars and 931 forks. The repository was created 2025-03-03. GitHub's language breakdown is led by Rust, then Python. The README says the core is Rust, with a Python SDK you install using pip install -U cocoindex
  • ›Latest GitHub release on that date was v1.2.0, published 2026-11-09. It adds a Discord source connector, experimental Google Drive sign-in for a personal account, and experimental data dependencies for memoized functions
  • ›The README badge says Python 3.10–3.13. The 1.2.0 package on PyPI (uploaded 2026-11-09) requires Python >=3.11, lists 3.11 through 3.14, and is classified Production/Stable. The separate cocoindex-code 0.2.43 package (uploaded 2026-11-05) is classified Alpha. Trust the package metadata over the badge
  • ›The README says a source change updates the affected records and retires stale rows without touching anything that did not change. The core is Rust

limits

  • ›The README opens with '70% token savings' and does not link a benchmark or a method. Do not treat that line as a measured saving
  • ›cocoindex-code[full] bundles sentence-transformers so embeddings run in-process, with no API key. The README says those dependencies are about 1 GB of torch and transformers. The slim install is LiteLLM-only: a cloud provider with an API key, or a local Ollama server with no key and no per-token cost. The local example is model: ollama/nomic-embed-text, and OLLAMA_API_BASE if the server is not at http://localhost:11434
  • ›As an MCP server, ccc mcp exposes one tool, search. It does not look up callers or rename a symbol. The README also says ccc grep depends on a cocoindex code_match feature that, until it ships in a released cocoindex, requires a local cocoindex build
  • ›With [full] installed, ccc init defaults to the in-process model Snowflake/snowflake-arctic-embed-xs. ccc init also recognizes the nomic-ai code models nomic-ai/CodeRankEmbed and nomic-ai/nomic-embed-code and fills in their indexing and query settings. The README shows those as sentence-transformers models, says CodeRankEmbed retrieves code better than the default, and says it is 137M parameters, needs about 1 GB of VRAM, and has an 8192-token context window

why #1

Ranked #1 in Context & Indexing. The job is handing an agent the right code and docs without paying to reread the repo. A default cocoindex-code MCP search returns at most about 1,500 tokens of code, five chunks of about 300 tokens, instead of whole files, and a later index run skips files that did not change. The same page says there is no single saving that holds for every repo, and that callers and references need Serena or the licensed Code Plus product. Serena ranks second as that symbol tool. Sourcegraph ranks third as the enterprise code-search instance. Repomix ranks fourth as a one-shot pack of the repo into a file. This order follows the job, not GitHub stars. The scores are unmeasured placeholders, and the site does not display them.

sources

open cocoindex.io ↗

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 ↗
sponsor this spot →