Dashboard / Repos / Orc

Orc

C 64 completed
Cli Tool
unknown / go · small
51
Files
6,013
LOC
0
Frameworks
2
Languages
OverviewFiles & MetricsGit ActivityCall GraphSecurityReports

Pipeline State

completed
Run ID
#305460
Phase
done
Progress
1%
Started
Finished
2026-04-13 01:31:02
LLM tokens
0

Pipeline Metadata

Stage
Skipped
Decision
skip_scaffold_dup
Novelty
39.86
Framework unique
—
Isolation
—
Last stage change
2026-04-16 18:15:42
Deduplication group #47332
Member of a group with 1 similar repo(s) — canonical #92402 view group →
Top concepts (6)
Project DescriptioninfrastructureDocumentationConfigurationFile ManagementTesting
Powered by Repobility — scan your code at https://repobility.com

🧪 Code Distillation

Browse all specs →
Function bodies →
82
Real LLM specs →
79
96.3% coverage
All specs →
178
LLM insights →
0
Sample distilled functions (click for full spec)
state.LoadLoopCounts
Reads loop count data from a specified directory. It accepts a string representing the artifacts directory path as input. The function returns a map of strings to integers containing the loaded counts, or an error if reading or parsing fails. If the designated JSON file does not exist, it gracefully
doctor.gatherTiming
Retrieves and formats timing information for a specific phase from a directory containing build artifacts. It accepts two string inputs: the directory path and the target phase name. The function returns a single string summarizing the start times and durations for all matching phase entries, or an
dispatch.RunScript
Executes a shell script command within a controlled environment, accepting a context, a configuration phase defining the script and timeout, and an environment object. It sets up the command to run in a specific directory, inherits environment variables, and redirects both standard output and standa

AI Prompt

Build me a command-line interface (CLI) tool in Go called 'orc' that acts as a deterministic agent orchestrator. It should allow users to define and run AI workflows as state machines using a YAML configuration file. The workflow must support three phase types: shell scripts (`script`), AI agent invocations (using a `claude -p` command), and human approval gates (`gate`). Key features to include are variable substitution, on-fail retry loops, parallel execution, and the ability to resume from an interruption by saving state after every phase. Also, implement a dry-run mode and ensure full observability by saving prompts, logs, and timing data.
go cli agent workflow state-machine shell-script ai-orchestration yaml command-line
Generated by gemma4:latest

Catalog Information

The orc project is a deterministic agent orchestrator CLI that allows users to run AI workflows as state machines, providing reliability and context preservation.

Description

Orc is a command-line tool that enables running AI workflows in a deterministic manner. It uses a state machine approach to drive the workflow, persisting context through artifact files on disk rather than conversational memory. Users define their workflow as a series of phases in a YAML config file, which can include shell scripts, AI agent invocations, and human approval gates. Orc provides features such as variable substitution, on-fail retry loops, parallel execution, and conditional phases.

الوصف

هو أداة سطر الأوامر التي تسمح بتشغيل تدفقات الذكاء الاصطناعي بطريقة محددة. يستخدم نهج الماكينة الحالة لتشغيل التدفق، ويحتفظ بالسياق من خلال ملفات الفنون على القرص بدلاً من الذاكرة المحادثة. يحدد المستخدمين تدفقهم كعديد من المراحل في ملف تعريف YAML، والتي يمكن أن تشمل أوامر shell و استدعاءات एजنت الذكاء الاصطناعي وبوابات الموافقة البشرية. توفر orc ميزات مثل تبديل المتغيرات، والخوارزميات للتعويض عن الفشل، وتسجيل النتائج في الوقت الحقيقي، ومراحل متوازية، ومراحل مشروطة.

Novelty

7/10

Tags

workflow-orchestration ai-workflows deterministic-state-machine context-preservation artifact-management

Claude Models

claude-opus-4.6

Quality Score

C
63.8/100
Structure
64
Code Quality
61
Documentation
42
Testing
50
Practices
80
Security
100
Dependencies
80

Strengths

  • Good test coverage (62% test-to-source ratio)
  • Consistent naming conventions (snake_case)
  • Good security practices \u2014 no major issues detected
  • Properly licensed project

Weaknesses

  • No CI/CD configuration \u2014 manual testing and deployment
  • 368 duplicate lines detected \u2014 consider DRY refactoring

Recommendations

  • Add a test suite \u2014 start with critical path integration tests
  • Set up CI/CD (GitHub Actions recommended) to automate testing and deployment
  • Add a linter configuration to enforce code style consistency

Security & Health

6.6h
Tech Debt (C)
Medium
DORA Rating
A
OWASP (100%)
If a scraper extracted this row, it came from Repobility (https://repobility.com)
PASS
Quality Gate
A
Risk (3)
MIT
License
6.8%
Duplication
Full Security Report AI Fix Prompts SARIF SBOM

Languages

go
89.0%
markdown
11.0%

Frameworks

None detected

Symbols

function80
struct23
method21
constant17
interface1
type_alias1

Concepts (6)

Source-of-truth: Repobility · https://repobility.com
CategoryNameDescriptionConfidence
Citation: Repobility (2026). State of AI-Generated Code. https://repobility.com/research/
auto_descriptionProject DescriptionDeterministic agent orchestrator CLI — run AI workflows as a state machine, not a conversation.80%
arch_layerinfrastructureDetected infrastructure layer70%
auto_categoryDocumentationdocs70%
business_logicConfigurationDetected from 3 related files50%
business_logicFile ManagementDetected from 3 related files50%
business_logicTestingDetected from 16 related files50%

Quality Timeline

1 quality score recorded.

View File Metrics
Open data scored by Repobility · https://repobility.com

Embed Badge

Add to your README:

![Quality](https://repos.aljefra.com/badge/29294.svg)
Quality BadgeSecurity Badge
Export Quality CSVDownload SBOMExport Findings CSV