Dual-Graph — Compounding Context for Claude Code & Codex CLI
A context engine that makes Claude Code and Codex CLI 30-45% cheaper without sacrificing quality. It builds a semantic graph of your codebase and pre-loads the right files into every prompt — so Claude spends tokens reasoning, not exploring.
Works on macOS, Linux, and Windows. Supports any project size.
Join the community: discord.gg/ptyr7KJz
How It Works
You run: dgc /path/to/project
↓
1. Project scanned → semantic graph built (files, symbols, imports)
2. You ask a question
3. Graph identifies the relevant files → packs them into context
4. Claude gets your question + the right code already loaded
5. Fewer turns, fewer tokens, better answers
Token savings compound across a session. The graph remembers which files were read, edited, and queried — each turn gets cheaper.
Results
Benchmarked across 80+ prompts (5 complexity levels) on a real-world full-stack app:
| Metric | Without Dual-Graph | With Dual-Graph |
|---|---|---|
| Avg cost per prompt | $0.46 | $0.27 |
| Avg turns | 16.8 | 10.3 |
| Avg response time | 186s | 134s |
| Quality (regex scorer) | 82.7/100 | 87.1/100 |
Cost wins on 16 out of 20 prompts. Quality equal or better on all complexity levels.
Install
macOS / Linux:
curl -sSL https://raw.githubusercontent.com/kunal12203/Codex-CLI-Compact/main/install.sh | bash
source ~/.zshrc # or ~/.bashrc / ~/.profile
Windows (PowerShell):
irm https://raw.githubusercontent.com/kunal12203/Codex-CLI-Compact/main/install.ps1 | iex
Windows (Scoop):
scoop bucket add dual-graph https://github.com/kunal12203/scoop-dual-graph
scoop install dual-graph
Prerequisites: Python 3.10+, Node.js 18+, Claude Code or Codex CLI. The installer detects missing tools and offers to install them via winget (Windows) or homebrew (macOS).
Usage
Claude Code (dgc)
dgc # scan current directory, launch Claude
dgc /path/to/project # scan a specific project
dgc /path/to/project "fix the login bug" # start with a prompt
Codex CLI (dg)
dg # scan current directory, launch Codex
dg /path/to/project # scan a specific project
dg /path/to/project "add tests" # start with a prompt
Windows
dgc . # from inside the project directory
dgc "D:\projects\my-app" # any drive, any path
dg "C:\work\backend" # Codex CLI
What It Does Under the Hood
- Scans your project — extracts files, functions, classes, import relationships into a local graph.
- Pre-loads context — when you ask a question, the graph ranks relevant files and packs them into the prompt before Claude sees it. No extra tool calls needed.
- Remembers across turns — files you've read or edited are prioritized in future turns. Context compounds.
- MCP tools available — Claude can still explore the codebase via graph-aware tools (
graph_read,graph_retrieve,graph_neighbors, etc.) when it needs to go deeper.
All processing is local. No code leaves your machine.
Data & Files
All data lives in <project>/.dual-graph/ (gitignored automatically).
| File | Description |
|---|---|
info_graph.json |
Semantic graph of the project: files, symbols, edges |
chat_action_graph.json |
Session memory: reads, edits, queries, decisions |
context-store.json |
Persistent store for decisions/tasks/facts across sessions |
mcp_server.log |
MCP server logs |
Global files in ~/.dual-graph/:
| File | Description |
|---|---|
dgc.ps1 / dg.ps1 |
Launcher scripts (auto-updated) |
venv/ |
Python virtual environment for dependencies |
version.txt |
Current installed version |
Configuration
All optional, via environment variables:
| Variable | Default | Description |
|---|---|---|
DG_HARD_MAX_READ_CHARS |
4000 |
Max characters per file read |
DG_TURN_READ_BUDGET_CHARS |
18000 |
Total read budget per turn |
DG_FALLBACK_MAX_CALLS_PER_TURN |
1 |
Max fallback grep calls per turn |
DG_RETRIEVE_CACHE_TTL_SEC |
900 |
Retrieval cache TTL (15 min) |
DG_MCP_PORT |
auto (8080-8099) | Force a specific MCP server port |
Context Store
Decisions, tasks, and facts from your sessions are persisted in .dual-graph/context-store.json and re-injected at the start of the next session. This gives Claude continuity across conversations.
You can also create a CONTEXT.md in your project root for free-form session notes.
Token Tracking
A token-counter dashboard is registered automatically with Claude Code:
http://localhost:8899
Usage from inside a Claude session:
count_tokens({text: "<content>"}) # estimate tokens before reading
get_session_stats() # running session cost
Self-Update
The launcher checks for updates on every run and auto-updates if a new version is available. No manual intervention needed.
Current version: 3.8.55
Privacy & Security
- All project data stays local. Graphs, session data, and code never leave your machine.
- The only outbound calls are:
- Version check — fetches a version string (no project data).
- Heartbeat — sends
machine_idandplatformonly. No file names, no code. - One-time feedback — optional rating after first day of use.
.dual-graph/is automatically added to.gitignore.
Community
Have a question, found a bug, or want to share feedback?
Join the Discord: discord.gg/ptyr7KJz
- Get help with setup
- Report bugs
- Share workflows
- Follow releases
1 maintainer
Metadata
1 maintainer
Release files for graperoot 3.10.19
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| graperoot-3.10.19.tar.gz | 1.3 MB | Without provenance | Details |
Built distributions (wheels)
Total release size: 34.6 MB
Release files / graperoot-3.10.19.tar.gz
| Download URL | graperoot-3.10.19.tar.gz |
|---|---|
| Size | 1.3 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
426a76fc77943caea63fc319f367cbbff53d7ec5a9048170380e6c541141920b
|
|
BLAKE2b-256 checksum How to use checksums |
886527636097ba591a3181684fb607798cdbf3b8d9bae4d3f1dee0965f8b1f31
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.15
|
Release files / graperoot-3.10.19-cp313-cp313-win_amd64.whl
| Download URL | graperoot-3.10.19-cp313-cp313-win_amd64.whl |
|---|---|
| Size | 773.1 kB |
| Tags | CPython 3.13 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
3a0fd43ef3d534d93a67904f37cea9a2f7f41ed95de4627a56fbe8c36198d092
|
|
BLAKE2b-256 checksum How to use checksums |
229f8f13e70ba5f236ca9153c59d1bad3ea2321fda9f71a6747e32cf5bb6bd84
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.15
|
Release files / graperoot-3.10.19-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.whl
| Download URL | graperoot-3.10.19-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.whl |
|---|---|
| Size | 6.7 MB |
| Tags | CPython 3.13 Linux glibc 2.17+ x86-64 |
|
SHA-256 checksum How to use checksums |
b5deb3c4e467ce8fbb3f91cf70437844ea143e7b55a278843dd2b45c3732d037
|
|
BLAKE2b-256 checksum How to use checksums |
7f695e5fb2d389d3ba159a8102b5af9144a9518a7d1c4dec7406f6007aa68af1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.15
|
Release files / graperoot-3.10.19-cp313-cp313-macosx_26_0_arm64.whl
| Download URL | graperoot-3.10.19-cp313-cp313-macosx_26_0_arm64.whl |
|---|---|
| Size | 937.2 kB |
| Tags | CPython 3.13 macOS 26.0+ ARM64 |
|
SHA-256 checksum How to use checksums |
f134cbbd13b8fc0965633a391bc96997ca9b707af82e514da27ccb22f261ed3c
|
|
BLAKE2b-256 checksum How to use checksums |
7dd2555f8d60c8264e7c4aaf9ac7eb8cf151b475ed49ce85880fd3fc55f8da4f
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.15
|
Release files / graperoot-3.10.19-cp312-cp312-win_amd64.whl
| Download URL | graperoot-3.10.19-cp312-cp312-win_amd64.whl |
|---|---|
| Size | 773.4 kB |
| Tags | CPython 3.12 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
52d57248dc0a172ec1853b416af37e4b026eed4c16f5adac758f422f9b3673e0
|
|
BLAKE2b-256 checksum How to use checksums |
53dd85cedba910c2c547a007a4683ae14424271871284b3cc98e24f38c8d0a70
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.15
|
Release files / graperoot-3.10.19-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl
| Download URL | graperoot-3.10.19-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl |
|---|---|
| Size | 6.7 MB |
| Tags | CPython 3.12 Linux glibc 2.17+ x86-64 |
|
SHA-256 checksum How to use checksums |
15e81d9468e16fa43b57add7473dcc364807e7eab31a1a3f9def7cb969760784
|
|
BLAKE2b-256 checksum How to use checksums |
4ecffb6b553522547bb1c0011b3ca1279042754f11b8ffce31ab5b37fd8ef25e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.15
|
Release files / graperoot-3.10.19-cp312-cp312-macosx_26_0_arm64.whl
| Download URL | graperoot-3.10.19-cp312-cp312-macosx_26_0_arm64.whl |
|---|---|
| Size | 941.5 kB |
| Tags | CPython 3.12 macOS 26.0+ ARM64 |
|
SHA-256 checksum How to use checksums |
ec0343b93f422986d0c7fcfdb996103d026a2eb2772cccc20b75fc5294cd3f33
|
|
BLAKE2b-256 checksum How to use checksums |
7791159d53a6219cf06aad3716b88f855fd224eec6f078f62214faaede4ecc8a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.15
|
Release files / graperoot-3.10.19-cp311-cp311-win_amd64.whl
| Download URL | graperoot-3.10.19-cp311-cp311-win_amd64.whl |
|---|---|
| Size | 826.4 kB |
| Tags | CPython 3.11 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
c71dc9e443258ed992e5177d1ccf0258b84b87ffc4db977dfafe45b1dd7ed58d
|
|
BLAKE2b-256 checksum How to use checksums |
98311900beb0df1390cf6baf9e475e26d1c8b7c69c78393a1f0456bd98327ac0
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.15
|
Release files / graperoot-3.10.19-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl
| Download URL | graperoot-3.10.19-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl |
|---|---|
| Size | 7.0 MB |
| Tags | CPython 3.11 Linux glibc 2.17+ x86-64 |
|
SHA-256 checksum How to use checksums |
338a86bd0ec4a4132eb8cf3b8128818e059ad0754499738057aab8ff332b7825
|
|
BLAKE2b-256 checksum How to use checksums |
122594e2c8c07f22ecbb9103bd53db991df54befc45f23fbf2c05b8454c8cc1b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.15
|
Release files / graperoot-3.10.19-cp311-cp311-macosx_26_0_arm64.whl
| Download URL | graperoot-3.10.19-cp311-cp311-macosx_26_0_arm64.whl |
|---|---|
| Size | 933.9 kB |
| Tags | CPython 3.11 macOS 26.0+ ARM64 |
|
SHA-256 checksum How to use checksums |
ceba0680dd5ee8495a2cdaf86d0454d453ce3589f10d8a2fe8d411ff21efbb11
|
|
BLAKE2b-256 checksum How to use checksums |
5f2daf99c073b2b3f8d24a65c5a75f17f15baeddfd7401e512c27e5afac8aba0
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.15
|
Release files / graperoot-3.10.19-cp310-cp310-win_amd64.whl
| Download URL | graperoot-3.10.19-cp310-cp310-win_amd64.whl |
|---|---|
| Size | 826.2 kB |
| Tags | CPython 3.10 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
79f9b5ed7df98f062f8645bb2e278e395b277f99f16541b5c6fb374b0257c03f
|
|
BLAKE2b-256 checksum How to use checksums |
894c3cae87aa6443af06bab44aaaaf34a4e2f6bbeed3e0d132f0916d425727c6
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.15
|
Release files / graperoot-3.10.19-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl
| Download URL | graperoot-3.10.19-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl |
|---|---|
| Size | 6.7 MB |
| Tags | CPython 3.10 Linux glibc 2.17+ x86-64 |
|
SHA-256 checksum How to use checksums |
6d90b63f58dd7bc306784e9b2b12d86c32058bd407b533eecc321cb5f92769dc
|
|
BLAKE2b-256 checksum How to use checksums |
4786e38e904ebc808fd46e864966c30559fcb82c78dc457b70c07e7ecd80de80
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.15
|
Security for graperoot 3.10.19
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.
No provenance found
None of the files in this release were uploaded with provenance metadata.
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.
