Skip to main content

gdm: AI coding agent for professional developers

Project description

gdm — AI Coding Agent

A terminal-native coding agent that reads your codebase, reasons over it, and edits files autonomously — with configurable autonomy, local model support, and a full audit trail.

Build status PyPI License: MIT


⚡ Quick start (30 seconds)

pipx install gdmcode
gdm version
gdm health
cd my-project && gdm "fix the login bug"

See docs/quick-start.md for a step-by-step walkthrough.


Why gdm?

  • Local-model support — run fully air-gapped with Ollama or vLLM; no data leaves your machine.
  • Autonomy slider — five levels from "ask everything" to "fully autonomous"; start low, build trust.
  • Transparent and controllable — explicit provider/model controls, hash-chained audit log, team policy enforcement.

Feature status

Reality-checked against docs/tasks-v2.

Feature Status Task(s)
Multi-model routing (Grok / Gemini / DeepSeek / Codex) ✅ implemented models-001/002/005
Local model support — Ollama / vLLM 🚧 in progress models-003
Cost tracking and budget caps ✅ implemented runtime-005
Session checkpoint / restore ✅ implemented core-002/003
Audit log with hash chain ✅ implemented enterprise-002
Team configuration and policy ✅ implemented enterprise-001
Web search (debug / research) ✅ implemented tools-003
Code index + whole-codebase mode ✅ implemented memory-001/005
Git workflow automation ✅ implemented autonomous-003
Verification loop 🚧 in progress autonomous-002
Self-healing debug loop 🚧 in progress autonomous-004
Multi-file orchestration 🚧 in progress autonomous-001
Impact analysis gate 🚧 in progress autonomous-005
Autonomy slider — 5 levels 🚧 in progress ide-004
VS Code extension ✅ implemented ide-001/002/003
Voice interface (PTT + streaming) 🚧 in progress voice-001/002/003
Remote / LAN server + phone UI 🚧 in progress remote-001/002/003
Chrome extension + bridge 🚧 in progress extensions-002
MCP protocol server 🚧 in progress integrations-003
GitHub Actions CI integration ✅ implemented integrations-001
Playwright browser automation 🚧 in progress tools-002
Sub-agent parallel execution ✅ implemented tools-005
RBAC (role-based access control) 📋 planned enterprise-003
Usage analytics dashboard 📋 planned enterprise-004
Hermetic sandbox ✅ implemented moonshot-002
Patch risk scoring 🚧 in progress moonshot-006
Impact graph smart test selection 🚧 in progress moonshot-007
CI eval pipeline 🚧 in progress evals-002
Continuous memory 🚧 in progress memory-003
Proxy/relay mode (geo-restricted regions) ✅ implemented proxy-001
OIDC identity integration 📋 planned

Installation

Prerequisite: Python 3.11+ and pip

python --version
python -m pip --version

Recommended (isolated environment):

pipx install gdmcode

pip:

pip install gdmcode

Development install:

git clone https://github.com/GedeonMatabaro/gdmcode
cd gdmcode
pip install -e ".[dev]"
gdm health

Note: The PyPI package is gdmcode. The command is gdm.


Configuration

gdm uses a 7-layer precedence system (highest wins):

CLI flags > env vars (GDM_*) > team policy > team preferences
         > project .gdm/config.toml > user ~/.config/gdm/config.toml > defaults

Quick setup:

gdm login grok        # or: gemini | deepseek | codex | all
gdm models            # list exact provider/tier -> model IDs
gdm --provider deepseek --model reasoner code

Secrets are stored in the OS keychain — never in TOML files.

Full configuration reference: docs/configuration.md


Enterprise

gdm includes audit and governance features suitable for team deployment:

  • Audit log — every tool call is logged with a hash chain for tamper detection.
  • Team policy.gdm/team.toml enforces autonomy caps, network allowlists, and git permissions.
  • RBAC — planned (enterprise-003).

See docs/security-hardening.md for deployment guidance.


Architecture

gdm runs a tool-calling agent loop: the model receives a task, selects tools from a registered registry, executes them (subject to injection checks, RBAC, and network policy), and writes the results back into context. Sessions are checkpointed to SQLite; memory is indexed for whole-codebase reasoning.

Full architecture diagram: docs/architecture.md


Contributing

See CONTRIBUTING.md. Issues and PRs welcome.


License

MIT — Copyright GedeonMatabaro

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

gdmcode-0.1.1.tar.gz (1.7 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

gdmcode-0.1.1-py3-none-any.whl (444.8 kB view details)

Uploaded Python 3

File details

Details for the file gdmcode-0.1.1.tar.gz.

File metadata

  • Download URL: gdmcode-0.1.1.tar.gz
  • Upload date:
  • Size: 1.7 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for gdmcode-0.1.1.tar.gz
Algorithm Hash digest
SHA256 61909a677aee1020ed87b3c7dd7588b85932364d195f9dd60e568d3baf5ac308
MD5 42dcf16c168bb1aba20ff18ba2b2591b
BLAKE2b-256 79ee0a39661960711762d7248a6dcf52336177aa56033ded36708801926ee76c

See more details on using hashes here.

File details

Details for the file gdmcode-0.1.1-py3-none-any.whl.

File metadata

  • Download URL: gdmcode-0.1.1-py3-none-any.whl
  • Upload date:
  • Size: 444.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for gdmcode-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 24c415e6060bbbb4cef122fa534dd32a80af28b6bf5e93709f06c4417951a275
MD5 6af46eb56607a34dea645a79839c1862
BLAKE2b-256 956d26841340282b930259df89068bbea52e72a223875cb69720033a7d6ed4f8

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page