CodeNib

ai.codenibPublished by codenib.aiv0.2.5Updated Nov 4, 2026

Source-linked CodeGraph exploration, ranked search, and static navigation for coding agents.

VerifiedSTDIODesktop onlyKnowledge & MemoryDeveloper Tools

Overview

AI-generated overview

CodeNib builds a local, source-linked code graph for a repository so coding agents can explore ranked code context and navigate definitions and references.

What you can do
  • Explore bounded code context with ranked source anchors and file/line citations
  • Navigate definitions and static references, including incoming and outgoing relationships
  • Pull a dependency subgraph in one call, up to depth 8
  • Index repositories across many languages, with graph backends for Python, Go, Rust, C/C++, C#, Java, Ruby, PHP, Kotlin, Scala, JavaScript and TypeScript
  • Export a saved repository Wiki with source citations
When to use it
Useful when a coding agent needs to locate where behavior is implemented in a larger multi-language repository and follow call paths beyond a single hop, rather than relying on plain grep and file reads. Best for teams already using Claude Code or Codex on local checkouts.
Requirements
Runs locally over stdio; requires Python 3.10+, Git, and Claude Code or Codex. Installed from PyPI as codenib with the graph and mcp extras, then initialized per repository with the codegraph init command. No model, API key or GPU is needed for the core CodeGraph path; language toolchains and prerequisites vary by language.
Before you install
Initialization accepts uncommitted edits and preserves the checkout, but indexing and rebuild costs should be counted. Static references may miss external or dynamic relationships, so source should be read before describing call paths. An optional grep-to-Jev route uses OpenRouter and sends selected code to remote models; that route is separate from the model-free core. The project is in beta and public interfaces may change.

Installation

In SourceWeft

  1. Open CodeNib in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

[CodeNib]

Find the right code. Follow its references.

Give Claude Code and Codex source context and typed graph navigation across languages.

71.4% code-block Recall@5 on 100 real issues.
Model-planned grep → Jev: +12.8 percentage points over the same grep candidates without reranking.
Experimental result · Method and limitations

Use with your agent  ·  Browse a Wiki  ·  Languages  ·  Reproductions  ·  Releases

[CI] [PyPI version] [Latest GitHub Release] [arXiv paper] [Hugging Face: #1 Paper of the Day] [Apache 2.0 license]

[Play a recorded Claude Code session on Requests: explore_context finds where authentication is stripped on redirects, then one dependency_subgraph call traces the four-hop caller chain from the public API]

▶ Watch the 15-second replay · real CLI output · waits condensed · Pinned source, transcript and setup details.

New in 0.2.5: saved repository Wikis and portable OKF export, Pyrefly-backed Python graphs, static entry-path navigation and call-path rule checks. Read the release notes.

Quickstart

Requires Python 3.10+, Git, and Claude Code or Codex. Initialization accepts uncommitted edits and preserves the checkout.

bash
python -m pip install "codenib[graph,mcp]"codenib codegraph init /path/to/your/repo

Then ask your agent: “Use CodeNib's explore_context to find where request retry behavior is implemented. Cite the files and lines.”

This shipping path builds local search and a typed symbol graph, then connects installed agent clients. It needs no model, API key, or GPU for CodeNib; your agent uses its own model. It is separate from the grep/Jev experiment above. Language toolchain and project prerequisites vary.

Setup and troubleshooting · Source exclusions · All MCP tools · Local Wiki

Why CodeNib

  • Inspect the evidence. Retrieve bounded code context with file and line references, then navigate definitions and static references. Read the source at each reference before describing a call path.
  • Use the same tools across languages. The registry tracks 14 language entries, including 12 with graph backends. Check capability and setup differences in the language matrix.
  • Compare methods on the same source. Pinned agent contracts, datasets, and scorer checks make the reproduction surface inspectable.
  • Share what you found. Export a Wiki with source citations to your own GitHub Pages, or browse the public examples.

How it compares

What an agent can ask each tool. Peer interfaces were checked against upstream docs on 2026-09-28. This compares capabilities, not benchmark scores.

ToolAsk in plain languageRelationships beyond one hopRelationships resolved byRuns
grep / readNo; literal or regexNoText matchLocal
CodeNib CodeGraphYes; ranked source anchors (explore_context)Incoming/outgoing static references; one dependency_subgraph call, depth ≤ 8SCIP/LSP indexers (compiler-resolved)Local
SerenaNo; symbol name or regexOne level per call (find_referencing_symbols)Live language server or IDELocal
CodeGraph (colbymchenry)Yes; FTS5 full-text (codegraph_explore)Yes; call paths in codegraph_exploreTree-sitter AST extractionLocal; telemetry opt-out
DeepWiki public MCPYes; generated answers (ask_question)No structured graph toolsGenerated WikiHosted

CodeNib's indexed references can include calls, fields, type uses and function values. Inspect the source to establish which references invoke a function; external and dynamic relationships may be missing. For a known string or file, your agent's native search and reads remain useful. Include indexing and rebuild costs when assessing graph navigation on your own tasks.

None of these repository tools needs its own model or API key; your agent uses its own model. Detailed comparison, sources and boundaries. CodeNib also includes an optional grep → Jev route using OpenRouter for planning and reranking; selected code goes to remote models. Authorization previews remain opt-in. The historical research result above is separate from the product evaluation and the model-free CodeGraph row.

Languages

Graph backends: Python, Go, Rust, C/C++, C#, Java, Ruby, PHP, Kotlin, Scala, JavaScript, and TypeScript. Swift and Lua support chunking/retrieval. Provider prerequisites and coverage differ by language.

The generated language matrix separates chunking, graph backends, incremental-backend support, and decoder parity. The product currently reuses or rebuilds views; file-level delta repair is not enabled.

Results and reproductions

Start hereWhat you can inspect
Context methods and support matrixEvery retrieval pipeline, LLM workflow and agent route, sorted by the views it reads and who controls the search
BenchmarksLocalization, agent-context and resolution layers, evidence levels, and the method × benchmark matrix over CodeNib Base/Synthesis, SWE-bench Lite, Loc-Bench, SWE-Explore, Agent Retrieval Bench and ContextBench
grep → Jev result100-issue retrieval comparison, candidate controls, model use and limitations
Agent integration matrixRevision-pinned LocAgent, Agentless, CoSIL, OrcaLoca and RepoNavigator contracts; compatibility does not imply reproduced paper scores
SWE-Explore validation1,020/1,020 real-output metric cells match the pinned official evaluator on a fixed 20-case run
DGX Spark deploymentLocal Wiki, CodeGraph and model serving on GB10; a deployment guide, not a token-saving benchmark

Documentation and community

Documentation · Architecture · Contributing · CI and testing · Changelog · Discord

CodeNib is in beta; public interfaces may change before a stable release. Historical research artifacts retain their published dataset identifiers.

Citation

If you use CodeNib in your research, please cite our arXiv paper:

bibtex
@misc{yu2026codenibmultiviewdataserving,      title={CodeNib: A Multi-View Data System for Serving Repository Context to Coding Agents},      author={Zhongming Yu and Hengjia Yu and Boqin Yuan and Shuting Zhao and Yizhao Chen and Aryan Dokania and Mihir Jagtap and Jiayu Chang and Yitong Ma and Yash Jayswal and Wentao Ni and Hejia Zhang and Zhaoling Chen and Gangda Deng and Jishen Zhao},      year={2026},      eprint={2607.25431},      archivePrefix={arXiv},      primaryClass={cs.SE},      url={https://arxiv.org/abs/2607.25431},}

CodeNib is licensed under Apache 2.0.

Source: README.md at commit 35f2fea

Tools

0
SourceWeft started this package once in an isolated sandbox, without credentials, to list its tools. That failed: the server did not start.

Version history

3
  1. v0.2.5LatestNov 4, 2026
  2. v0.2.4Sep 27, 2026
  3. v0.2.3Sep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts