$ buildwith diff cocoindex repomix

CocoIndex vs Repomix

Both are in Context & Indexing, where we rank CocoIndex #1 and Repomix #4. 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 Repomix if you want one file of a repository, or a compressed signature view of it, to hand to a chat model or an agent, and you do not want to run an index.

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 ↗

Repomix

#4 · Free / OSS

Repomix packs a repository into a single file for an LLM. The default output is XML (repomix-output.xml). Markdown, JSON, and plain text are the other styles. It respects .gitignore, runs Secretlint so files that match known credential formats are left out, and prints token counts for each file and for the whole pack. Run it with npx repomix@latest, or install it with npm install -g repomix, yarn, bun, or brew install repomix. --include and --ignore take globs. --remote packs a public GitHub repository. The site also documents Docker and a GitHub Action.

for Someone who wants to paste a codebase into ChatGPT, Claude, Gemini, Grok, or another chat, or who wants an agent to pack a repo itself. The site says this uses the subscription you already have, and that the CLI can read private repositories because it uses git installed on your machine. It is a pack step, not a hosted index.

use this if you want one file of a repository, or a compressed signature view of it, to hand to a chat model or an agent, and you do not want to run an index.

pricing

  • Open source Free

    The site documents npx, a global npm install, Homebrew, bun, yarn, and a Docker image, and it does not list an account, a subscription, or a paid tier.

features

  • ›repomix --mcp starts an MCP server. The guide lists pack_codebase, pack_remote_repository, read_repomix_output (by output id, with a line range), and grep_repomix_output. Claude Code: claude mcp add repomix -- npx -y repomix --mcp. Cursor, VS Code, Cline, and Claude Desktop use the same npx command
  • ›--sandbox confines MCP file tools to one workspace. Absolute paths, ~, and .. are refused. In that mode the server also registers file_system_read_file and file_system_read_directory, and it does not register remote packing. The guide says this is application-level confinement, not an OS sandbox
  • ›pack_codebase can set compress, include and ignore globs, per-file output patterns, and the output style. Without --sandbox, pack_codebase loads the repomix.config in the directory it packs. The guide says to use --sandbox when the assistant might pack an untrusted checkout
  • ›pack_codebase's compress flag is described as Tree-sitter compression that removes implementation details. The guide says this reduces token usage by about 70% and does not show the count behind that figure. The same description says compression is generally not needed, because grep_repomix_output can read the pack in pieces
  • ›topFilesLength defaults to 10, the number of largest files by size shown in the metrics summary

strengths

  • ›MIT license. On 2026-11-11 the GitHub API reported 29,222 stars and 1,633 forks. The repository was created 2024-07-13. Primary language is TypeScript
  • ›Latest release on that date was v1.19.0, published 2026-11-08. The notes say the MCP server moved to the TypeScript SDK v2, long packs report progress and cancel with the client, and a path inside a remote URL is ignored unless you add an --include glob. They also name a generate_skill tool. The MCP guide page does not list that tool
  • ›The v1.19.0 notes say an MCP pack_codebase always runs the secret scan, even if a config file in the packed directory turns security.enableSecurityCheck off. A normal CLI run still follows the config
  • ›There is no index to build and no embedding model. A pack is a file you can read, grep, or hand to a model that has no MCP client

limits

  • ›The guide calls --compress experimental. It keeps function and method signatures, interface and type definitions, and class structures and properties. It removes implementations, loop and conditional details, and internal variable declarations. The compressed file does not contain function bodies
  • ›The guide says compression is for reducing token count and does not publish a measured reduction, a corpus, or a before-and-after count

why #4

Ranked #4 in Context & Indexing. Repomix is the shortest path from a repository to a file a model can read: one command, no index, no account on the site. It ranks below CocoIndex, Serena, and Sourcegraph because the pack is still a snapshot in the prompt. A default pack can be more text than a chunk search, a symbol lookup, or a search against an indexed copy of the repo, and the compressed form drops function bodies. Use it when you want the whole repo, or a signature-only view, in one shot. The scores are unmeasured placeholders and are not shown.

sources

open repomix.com ↗
sponsor this spot →