Sculptor: parallel agents isolated in local Docker containers
Sculptor flips the Devin model: instead of a single autonomous agent in an opaque cloud sandbox, Sculptor launches multiple AI agents in parallel inside local Docker containers that you watch and control. Each agent works on a distinct part of the codebase in its own isolated environment. You can open a shell in the container, check the logs, stop the agent, or restart it with a new instruction. Container isolation also avoids conflicts between agents. Target audience: Mac and Linux developers who want the power of parallel agents without handing control to a cloud vendor. Great option for privacy-sensitive teams.
For who
Mac/Linux developers, privacy-sensitive product teams, and DevOps tinkerers who want to run parallel AI agents locally.
Input
Objectifs de taches par agent, configuration des conteneurs (langage, dependances), cle LLM.
steps (6)
Install Sculptor
infoInstall Sculptor via Homebrew (Mac) or the official script (Linux). Docker Desktop or Docker Engine is required.
Connect an LLM
infoProvide an API key (Anthropic, OpenAI) or configure a local model via Ollama.
Open a project
infoPoint Sculptor at a local repo. It spins up a base container with detected dependencies.
Run multiple agents
infoStart 2 to 8 parallel agents, each with its own goal. Each agent runs in its container.
Supervise and intervene
infoBrowse each container's logs, jump in manually, stop or restart an agent mid-run.
Consolidate work
infoMerge the Git branches produced by each agent into main after review.
Output
Branches Git independantes par agent, logs de conteneur, diffs prets pour merge.
Example
Input
Launch 3 agents: Agent A = "Write missing tests for /api/billing"; Agent B = "Optimize slow Postgres queries found in staging"; Agent C = "Migrate ESLint to Biome".
Output
Sculptor spins up 3 Docker containers, each on its Git branch. You follow the logs: Agent A finishes in 8 minutes with 24 tests; Agent B produces 3 query refactors; Agent C completes the migration. You merge all 3 branches after review.
Customization
| Parameter | Description | Default |
|---|---|---|
| Nombre d'agents | Agents paralleles (2 a 8). | 3 |
| Image conteneur | Base Docker utilisee (auto-detect ou image custom). | auto-detect |
| Mode LLM | API cloud (Anthropic/OpenAI) ou local (Ollama). | Anthropic |