← Open Source
owainlewis

machinist

Open source software factory infrastructure for advanced AI coding workflows.

InfrastructureObservabilityMake world agent-readyGo
Open on GitHub
Momentum
+1stars in 24 hours+0.2%
506
Stars
98
Forks
3
Contributors
Created 2026-07-16 · Updated 2026-10-16 · #6873 today
Top developers

owainlewis/machinist is ranked 6,873 with 506 stars.

Same-category comparison

owainlewis/machinist is ranked 6,873 among these 8 peers; xiaods/k8e is ranked 6,881.

Same-category comparison
NameRankMetrics
stormzhang/token-tracker6,813
Language:
Python
Stars:
532
Forks:
60
IBM/aihwkit6,843
Language:
Jupyter Notebook
Stars:
519
Forks:
197
Description:
IBM Analog Hardware Acceleration Kit.
NVIDIA/flashdreams6,849
Language:
Python
Stars:
516
Forks:
64
Description:
high-performance inference and serving library for interactive autoregressive video and world models.
nmhjklnm/cac6,853
Language:
Shell
Stars:
515
Forks:
61
Description:
Isolate, protect, and manage your Claude Code.
xiaods/k8e6,881
Language:
Go
Stars:
504
Forks:
35
Description:
k8e.sh - OpenSource Agentic AI Sandbox Matrix.
NVIDIA/cuQuantum6,883
Language:
Jupyter Notebook
Stars:
503
Forks:
102
Description:
Home for cuQuantum Python & NVIDIA cuQuantum SDK C++ samples.
onnx/onnx6,923
Language:
Python
Stars:
21,589
Forks:
4,053
Description:
Open standard for machine learning interoperability.
labring/sealos6,939
Language:
Go
Stars:
18,370
Forks:
2,477
Description:
Deploy real projects from GitHub or your AI coding agent, then keep them running with AI-powered operations.
Key parameters and specifications
Key parameters and specifications
ParameterValue
LanguageGo
CategoryInfrastructure
SubcategoryObservability, Make world agent-ready
KeywordsAgent-ready APIs, DevOps, Guardrails, Tool use
Stars506
Forks98
Contributors3
Created date2026-07-16
Updated date2026-10-16
Stars in 1 day1
Rank6,873
Previous rank4,491
Rank change-2,382
7-day stars rank19,349
Previous 7-day stars rank19,333
7-day stars rank change-16
Total stars rank19,171
Previous total stars rank19,184
Total stars rank change13
CountryUK
README summary

Run coding agents on infrastructure you control. Local, VM, and Kubernetes jobs with GitHub pull-request delivery. Website · Documentation · Configuration · Workflow examples Machine section · supervised agent system · exploded assembly Machinist is an open-source software factory implementation. It runs on your machine, keeps repository access and credentials local, and records the work from request to handoff. Commands can invoke Codex, Claude Code, another agent CLI, a test runner, a shell script, or repository-owned orchestration. Please note: this is early

access software and subject to change. Why Machinist **One controlled entrypoint. ** Workers expose named commands and repositories, never arbitrary shell text or machine-local paths. ** Use any executable that accepts a prompt on standard input. ** Repositories, credentials, model aliases, and executor configuration stay on the worker. ** Stream output, retain durable events and artifacts, and track terminal outcomes, duration, and reported token use. ** Approve specifications when needed, follow independent review, and merge the pull request yourself. Quick start Build and initialize

Machinist: Start the app: Open the printed local URL. Connect your GitHub App, choose a repository and agent, and verify the connection with PING. Agents run on your computer, a VM, or a configured Kubernetes cluster. Sign in to the coding CLI on its execution host. Multiple projects Open **Projects → Add project** to connect another repository. Adding a project preserves your existing projects, agent, and execution target. Each repository gets its own checkout, and runs and automations choose from the

configured list. The project list is saved on the control-plane host and restored after restart. Only repositories granted to your GitHub App appear. Use **Manage GitHub access** to grant more repositories, then **Refresh repositories**. Local and Kubernetes runners reload while idle. For a VM, stop its existing worker, download the updated VM setup from Projects, and run it to clone and register all configured projects. How execution works Use **New run** to describe work or link a GitHub issue

. Choose one of two modes: **Standard pipeline:** Triage → optional Spec → Build → independent Review. Review findings return to the same branch and PR for up to three repair rounds. **Single agent:** one agent completes an operational task end to end. Use it for one-off jobs and automations. Requested code, documents, and reports use PR delivery. Questions and checks without file changes can return a result directly. Internal prompts, handoffs, and run history stay private in Machinist. GitHub holds published issues

, specs, code, and PRs. For scripts and direct CLI use, maps a named command to a fixed executable and runs it in the supplied repository. Existing sequence workflows remain available to CLI users; the app offers the two modes above. md for development setup and pull-request expectations. Machinist is released under the MIT License. Local jobs **New run** offers two modes. **Standard pipeline** runs Triage, optional Spec, Build, independent Review, and human merge. **Single agent** runs one operational task

or automation without a separate reviewer. Requested repository changes still use PR delivery and human merge; unchanged operational tasks return

Frequently asked questions

How many stars and forks are recorded?

owainlewis/machinist has 506 stars and 98 forks.

What is the repository rank?

owainlewis/machinist is ranked 6,873.

What language and category are recorded?

owainlewis/machinist has 506 stars, uses Go and belongs to Infrastructure.

Which repository is closest in rank?

owainlewis/machinist is compared with xiaods/k8e, ranked 6,881 with 504 stars.

README

Run coding agents on infrastructure you control.

Local, VM, and Kubernetes jobs with GitHub pull-request delivery.

Website · Documentation · Configuration · Workflow examples

Machine section · supervised agent system · exploded assembly

Machinist is an open-source software factory implementation. It runs on your machine, keeps repository access and credentials local, and records the work from request to handoff. Commands can invoke Codex, Claude Code, another agent CLI, a test runner, a shell script, or repository-owned orchestration.

Please note: this is early access software and subject to change.

Why Machinist

  • One controlled entrypoint. Workers expose named commands and repositories, never arbitrary shell text or machine-local paths.
  • Bring your own harness. Use any executable that accepts a prompt on standard input.
  • Keep authority local. Repositories, credentials, model aliases, and executor configuration stay on the worker.
  • Inspect every run. Stream output, retain durable events and artifacts, and track terminal outcomes, duration, and reported token use.
  • Review before merging. Approve specifications when needed, follow independent review, and merge the pull request yourself.

Quick start

Build and initialize Machinist:

git clone https://github.com/owainlewis/machinist.git
cd machinist
mkdir -p ./bin && go build -o ./bin/machinist ./cmd/machinist
./bin/machinist init

Start the app:

./bin/machinist start

Open the printed local URL. Connect your GitHub App, choose a repository and agent, and verify the connection with PING. Agents run on your computer, a VM, or a configured Kubernetes cluster. Sign in to the coding CLI on its execution host. See the setup guide.

Multiple projects

Open Projects → Add project to connect another repository. Adding a project preserves your existing projects, agent, and execution target. Each repository gets its own checkout, and runs and automations choose from the configured list. The project list is saved on the control-plane host and restored after restart.

Only repositories granted to your GitHub App appear. Use Manage GitHub access to grant more repositories, then Refresh repositories. Local and Kubernetes runners reload while idle. For a VM, stop its existing worker, download the updated VM setup from Projects, and run it to clone and register all configured projects.

How execution works

Use New run to describe work or link a GitHub issue. Choose one of two modes:

  • Standard pipeline: Triage → optional Spec → Build → independent Review. Specifications wait for approval. Review findings return to the same branch and PR for up to three repair rounds. You decide when to merge.
  • Single agent: one agent completes an operational task end to end. Use it for one-off jobs and automations.

Requested code, documents, and reports use PR delivery. Questions and checks without file changes can return a result directly. Internal prompts, handoffs, and run history stay private in Machinist. GitHub holds published issues, specs, code, and PRs.

For scripts and direct CLI use, machinist run maps a named command to a fixed executable and runs it in the supplied repository. Existing sequence workflows remain available to CLI users; the app offers the two modes above. See the command and workflow reference.

Go deeper

Guide What it covers
Documentation Choose the right setup and operations guide
Local factory GitHub App setup, agent jobs, review, and recovery
Configuration Commands, executors, workers, models, and repositories
Development Build, test, and work on Machinist locally
VM deployment Run the control plane and worker as services
Automations Save jobs and run them manually or on a schedule

Contributing

Read CONTRIBUTING.md for development setup and pull-request expectations. Security issues should follow SECURITY.md.

Machinist is released under the MIT License.

Local jobs

New run offers two modes. Standard pipeline runs Triage, optional Spec, Build, independent Review, and human merge. Single agent runs one operational task or automation without a separate reviewer. Requested repository changes still use PR delivery and human merge; unchanged operational tasks return a result. There is no custom workflow editor. The compact table includes stage progress dots.

API clients set recipe to factory or single and supply a stable client_request_id. Repeating the same request after a lost response returns the same job. A changed payload with that ID returns 409. Existing workflow: "factory" submissions remain compatible.

On upgrade, the app snapshots factory.db into jobs.db and archives the old store. Back up the full private runtime directory, including worker outputs. Imported blocked jobs are held private until explicitly reviewed and released. See local job behavior.

Kubernetes runners

Keep the control plane local or on a VM and run individual agent attempts in gVisor Kubernetes Jobs. The first target supports a dedicated Codex subscription login, serialized refresh, restricted egress and trusted GitHub PR publication. See Kubernetes setup and recovery.

Nearby in the ranking
Similar items