My AI coding setup was split in two: cloud subscriptions and APIs (Claude Code, Codex, Gemini CLI) on one side, local open-weight models (Ollama / vLLM) on the other, and four terminal windows running parallel git worktree loops on my machine.
Three things kept bugging me:
Getting local and cloud models to collaborate was clunky. I wanted frontier models debating specs and reviewing diffs, and fast or local GPU models grinding through implementation — without manually copying plans between tools.
Ideas don't only happen at the keyboard. Half my best product fixes hit me away from my desk, with no clean way to feed an idea into an autonomous pipeline and check on it safely from my phone.
Host security was an accident waiting to happen. Every local agent was running under my OS user with read access to ~/.ssh, ~/.aws, and live Git push tokens.
So I built (GitSeed · https://github.com/gitseed-dev/gitseed) — and today I'm open-sourcing the core platform under Apache 2.0.
What changed in my daily workflow
Capture anywhere, pick up anywhere: I can toss a rough Seed into the pipeline from the CLI, web, or even voice on my watch, let agents draft the spec and run tests in isolated containers, approve a review gate from my phone, and drop into an in-browser terminal or VS Code on desktop when something needs a human touch.
Frontier brains + local muscle: Up to 3 models run in parallel for Second Opinions during Ideate, Plan, or Review before locking the spec. Then Execute runs against LiteLLM-capped API keys, local GPUs (with no external model API traffic), or opt-in single-user Personal Mode (subject to your provider's subscription terms).
Agents hold zero Git credentials: Every stage splits into prepare → agent → finalize containers. finalize mounts /workspace read-only after the agent exits, blocks edits to protected paths, scans diffs for leaked secrets, pushes from a clean .git directory, and signs an Ed25519 audit receipt (gitseed.receipt.v1) onto the PR.
Works on Local Folders too: Point it at a local directory on your laptop before setting up any GitHub App — merged changes fast-forward back into your working tree without clobbering uncommitted edits.
Honest limits
Container isolation doesn't stop an agent from writing buggy logic inside normal source files (Review + human diff review are still essential), and Personal Mode estimates spend from token telemetry rather than enforcing a proxy dollar cutoff.
If you're mixing local GPUs and cloud coding agents on your own projects, I'd love to hear what your workflow looks like — repo and 3-step Docker Compose setup are at https://github.com/gitseed-dev/gitseed.
Trent Seed
Top comments (0)