Skip to main content

devkb

PyPI License: Apache-2.0 DOI

A knowledge graph of your repository for software development agents. Agents answer "what calls this, what breaks, which tests" in one step instead of searching file by file: 55% cheaper, with better answers, in our benchmark.

Median cost per task: plain search $0.070 (quality 0.931); devkb 12 tools $0.059, 18% cheaper (0.955); devkb 7 tools $0.040, 38% cheaper (0.963); devkb pack $0.025, 55% cheaper (0.981)

1. What devkb is

  • A graph built from your source and git history: functions, calls, tests, routes, errors, configuration, commits, pull requests, tickets (ontology).
  • Packs: one command answers a whole question (who calls this, what breaks, which tests to run), each item with the source line that proves it, and a statement of what the graph could not see.
  • An MCP server giving agents the same answers as tools, for Claude Code, Codex and any MCP client.

Everything runs locally: devkb reads files and runs git, never your code (unless devkb.json opts in), and the graph never leaves your machine.

Languages

Language Status What devkb understands
Python ✅ Supported functions, classes, calls (through imports, re-exports, typed objects, base classes), tests, FastAPI/Flask routes, raised and logged errors, environment variables; every pack
TypeScript, TSX 🟡 Partial functions, components, classes, and the HTTP calls they make to backend routes; not calls between them
JavaScript (.js, .mjs) 🟡 Partial as TypeScript
C# ✅ Supported classes, structs, interfaces, records, methods, constructors, properties, local and extension methods; calls through typed receivers, call results (a.B().C(), await, var, foreach), property chains, lambda parameters (builder lambdas, LINQ), static calls and new T(); extension methods and overloads chosen by receiver type and by argument count and declared types; a table of .NET's common types (bases, members, conversions); xUnit/NUnit/MSTest tests; every pack. Checked against the compiler on MediatR, FluentValidation, Polly, Jellyfin and EF Core. Not: generic type inference, overload betterness, dynamic, LINQ query syntax, third-party types' hierarchies
Odoo XML 🟡 Partial templates and menus
Bash / shell ⬜ Not yet files and history only
C, C++ 🟡 Partial definitions, calls, tests, throw/assert/log-macro messages. Limits: no preprocessor expansion, no overload resolution, no type inference; an answer says Incomplete where a call could not be attributed
Java, Rust, Go, others ⬜ Not yet files and history only

"Files and history" is the language-independent layer every repository gets: files, commits, pull requests and tickets.

2. How much it saves

Latest benchmark: the 7 open-source repositories in bench/repos.yaml, 57 tasks, 1,138 agent runs, the same model (Sonnet) in every arm, answers scored against truth computed from the source. Cost, turns and tokens are the median run; saving is per task against plain search, averaged over tasks; quality is the mean score:

Plain search devkb, 12 tools devkb, 7 tools devkb pack
Cost per task $0.070 $0.059 $0.040 $0.025
Saving — 18% 38% 55%
Quality (0–1) 0.931 0.955 (+0.024) 0.963 (+0.032) 0.981 (+0.050)
Turns 4 6 5 3
Context processed (tokens) 126k 169k 147k 75k
of which cache reads 123k 163k 141k 74k
of which new input and cache writes 8.3k 4.1k 2.0k 1.3k
Output tokens 1.4k 1.8k 1.3k 0.9k

Saving and quality gain by repository (95% intervals in the results):

Repository Tasks 7 tools: saving / quality pack: saving / quality
lnbits 10 53% / +0.032 66% / +0.049
Netflix Dispatch 8 45% / +0.040 61% / +0.081
Prefect 9 41% / −0.017 59% / +0.047
lattice-scan 12 36% / +0.052 51% / +0.058
Mealie 6 18% / +0.095 42% / +0.062
devkb 4 1% / +0.004 40% / +0.004
click 8 6% / +0.016 15% / +0.023

The saving is in call chains (66–77% on tasks that trace an error or a change to the route handlers that reach it); on one-hop questions, as in click, plain search is already good. An earlier pre-registered study (30 held-out tasks, 1,020 runs, two model sizes) found packs 41% cheaper and the lean tools 35% (study/; make verify recomputes it). Details and corrections: bench/results/2026-11-15-registry; add a repository: docs/BENCHMARK.md.

3. Set up

uv tool install "devkb[mcp]"      # or: pipx install "devkb[mcp]"
cd your-repo
devkb init --hooks

This builds the graph into .devkb/, adds a short devkb section to AGENTS.md and CLAUDE.md, registers the MCP server in .mcp.json, and rebuilds the graph after each commit. Your own content in those files is kept; devkb init --remove undoes it.

Install devkb as a tool, as above, so the devkb command is on your PATH: agents start the server from there, and a devkb installed only inside a virtual environment never starts (devkb init warns if that is the case).

Ask it directly:

devkb pack --project . refactor my_function     # who calls it, which tests
devkb pack --project . error "message text"     # which route handlers reach it
devkb pack --project . file path/to/file.py     # before editing a file

Your agent

Claude Code: nothing more to do. devkb init registered the server in .mcp.json and pointed CLAUDE.md at the instructions. Start claude in the repository, approve the devkb server when asked, and check it with /mcp. Or skip the install and devkb init and use the plugin, which brings the server, its instructions and a hook that builds the graph in the background (needs uv):

/plugin install devkb --marketplace namiq-ai/devkb

Cursor: add .cursor/mcp.json to the repository, then enable devkb under Settings → MCP:

{"mcpServers": {"devkb": {"command": "devkb", "args": ["mcp", "--project", ".", "--toolset", "lean-pack"]}}}

Codex: add to ~/.codex/config.toml:

[mcp_servers.devkb]
command = "devkb"
args = ["mcp", "--project", ".", "--toolset", "lean-pack"]

Codex and Cursor read the instructions in AGENTS.md; Claude Code reads them through CLAUDE.md.

What agents get by default (--toolset lean-pack): a pack tool that returns a whole answer in one call, and the seven single-question tools. The instructions tell them to ask for a pack when a question follows a chain (a file before editing, a change, an error) and to search as usual for a one-hop lookup, which is where the benchmark found the saving and where it did not. Measured with agents asking for the pack themselves (lnbits and Dispatch, 400 runs): 53% cheaper than plain search with the highest quality of any arm, against 42% for the seven tools alone (bench/results/2026-11-15-lean-pack).

Tried it on your repository? Tell us what happened, good or bad, in issue #25.

4. Licence and citation

Code: Apache-2.0. The study in study/ (paper, figures, pre-registration, data): CC BY 4.0. Benchmark results quote third-party code under its own licences (bench/results/NOTICE). Releases: docs/RELEASING.md.

Hung T. Le. Precomputed Context, Not More Tools: A Pre-Registered Study of Process Graphs for Coding Agents. 2026.

Metadata

Release files for devkb 0.2.6

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for devkb 0.2.6
File Size Uploaded Provenance Actions
devkb-0.2.6.tar.gz 339.4 kB With provenance Details for devkb-0.2.6.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for devkb 0.2.6
File Interpreter ABI Platform Actions
devkb-0.2.6-py3-none-any.whl Python 3 none any Details for devkb-0.2.6-py3-none-any.whl

Total release size: 632.2 kB

Release files / devkb-0.2.6.tar.gz

Download URL devkb-0.2.6.tar.gz
Size 339.4 kB
Tags Source
SHA-256 checksum
How to use checksums
12a743c897ebc032e4ffba2b43c0566dd25b22597f59593ad9857ce641c709a9
BLAKE2b-256 checksum
How to use checksums
1b62ed9c3d9bb685db33877081ae2995a0d6faa1d06bbda2771c8a92b0c96c02
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.12.8

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 16, 2026.

Transparency log

Release files / devkb-0.2.6-py3-none-any.whl

Download URL devkb-0.2.6-py3-none-any.whl
Size 292.9 kB
Tags Python 3
SHA-256 checksum
How to use checksums
61d2b92b88ee0734147c347861ffb83ee85068cc17ecfde58eab1b41ce221c27
BLAKE2b-256 checksum
How to use checksums
5bc5174401211ab9d825546f854e822ed5d78c136d6ac75db4faf39a779ba040
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.12.8

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 16, 2026.

Transparency log

Security for devkb 0.2.6

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Full provenance

Both files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for devkb-0.2.6.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 16, 2026.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page