{"id":49619738,"url":"https://github.com/infhorus/codedone.app","last_synced_at":"2026-05-05T01:01:35.355Z","repository":{"id":355692357,"uuid":"1229183605","full_name":"InfHorus/CodeDone.app","owner":"InfHorus","description":"Local, privacy-first agentic coding workspace in Go. CodeDone breaks large dev tasks into atomic serialized tickets, dispatches AI implementers one step at a time, and uses a Contre-Maître system to plan, supervise, review, and finalize work with lower token waste and higher reliability. Built to excel at very long tasks spanning multiple days.","archived":false,"fork":false,"pushed_at":"2026-05-04T20:20:23.000Z","size":10,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-05-04T21:33:01.489Z","etag":null,"topics":["ai","ai-agents","ai-assistant","ai-tools","cybersecurity","development"],"latest_commit_sha":null,"homepage":"https://codedone.app/","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/InfHorus.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-05-04T19:36:16.000Z","updated_at":"2026-05-04T20:21:49.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/InfHorus/CodeDone.app","commit_stats":null,"previous_names":["infhorus/codedone.app"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/InfHorus/CodeDone.app","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/InfHorus%2FCodeDone.app","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/InfHorus%2FCodeDone.app/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/InfHorus%2FCodeDone.app/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/InfHorus%2FCodeDone.app/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/InfHorus","download_url":"https://codeload.github.com/InfHorus/CodeDone.app/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/InfHorus%2FCodeDone.app/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32631058,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-04T10:08:07.713Z","status":"ssl_error","status_checked_at":"2026-05-04T10:08:02.005Z","response_time":58,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","ai-agents","ai-assistant","ai-tools","cybersecurity","development"],"created_at":"2026-05-05T01:01:19.827Z","updated_at":"2026-05-05T01:01:35.321Z","avatar_url":"https://github.com/InfHorus.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# CodeDone.app\n\nLocal, privacy-first agentic coding workspace in Go. CodeDone breaks large development tasks into atomic serialized tickets, dispatches AI implementers one step at a time, and uses a Contre-Maître system to plan, supervise, review, and finalize work with lower token waste and higher reliability. Built to excel at very long tasks spanning multiple days.\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://codedone.app/cdn/codedone-preview-1.png?v=2\" alt=\"CodeDone overview\" width=\"900\"\u003e\n\u003c/p\u003e\n\n## What is CodeDone?\n\nCodeDone is an agentic coding workspace designed for large, long-running software tasks. Instead of launching multiple chaotic agents in parallel, CodeDone uses a serialized agent pipeline: the **Contre-Maître** plans the work, generates a structured backlog, dispatches one ticket at a time to an Implementer, reviews each result, and finally hands the completed session to a Finalizer.\n\nThe goal is simple: let users build, refactor, or modify large projects from a single prompt while keeping the process auditable, controlled, and efficient.\n\n## Key Features\n\n### Serialized agent pipeline\n\nCodeDone uses a structured multi-agent workflow:\n\n- **Contre-Maître** plans, supervises, reviews, and controls the execution.\n- **Implementers** build one ticket at a time.\n- **Finalizer** validates the full session before marking the work complete.\n\nNo parallel chaos. No uncontrolled overlap. Each step is serialized, reviewable, and traceable.\n\n### Native Git workflow\n\nCodeDone is built directly around Git. Agents communicate through actual repository state, diffs, and file changes instead of vague status messages.\n\nThis makes every step auditable:\n\n- inspect what changed\n- review ticket-by-ticket progress\n- keep long sessions grounded in real code\n- work directly with GitHub-backed repositories\n\n### Multi-provider LLM support\n\nUse the models you want, where you want them.\n\nSupported providers include:\n\n- **OpenAI**\n- **Anthropic**\n- **DeepSeek**\n- **OpenRouter**\n- local LLMs, depending on your provider setup\n\nYou can configure different models for different agent roles, for example one model for the Contre-Maître and another for Implementers.\n\n### Configurable agent setup\n\nTune the execution strategy for your project:\n\n- choose how many Contre-Maîtres to spawn\n- choose how many Implementers to use\n- assign different models per role\n- control long-running sessions from a saved workspace state\n\n### Plan Mode\n\nBefore building, CodeDone can run in a planning/refinement mode where you discuss the task directly with the Contre-Maître.\n\nUse it to clarify scope, refine requirements, validate assumptions, and shape the backlog before any implementation starts.\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://codedone.app/cdn/codedone-preview-2.png?v=2\" alt=\"CodeDone planning mode and backlog generation\" width=\"900\"\u003e\n\u003c/p\u003e\n\n### Guidance system\n\nCodeDone includes built-in LLM guidance for different task types and project domains.\n\nGuidance can help agents behave correctly for work such as:\n\n- web design\n- frontend development\n- Go\n- C / C++ / C#\n- databases\n- shell and DevOps\n- cybersecurity review\n- game development\n- project-specific coding standards\n\nGuidance acts as persistent task-aware instructions that agents can query during a session.\n\n### Repo inspection and build tools\n\nAgents can inspect and operate on the target repository using tools such as:\n\n- file read\n- glob\n- grep\n- git introspection\n- shell execution\n- test runner integration\n\nThis lets agents understand the codebase before acting, apply targeted changes, and validate the result.\n\n### Long-running session support\n\nCodeDone is designed for tasks that are too large for a single prompt-response cycle.\n\nSessions can be:\n\n- paused\n- resumed\n- continued from a saved workspace\n- run across long workflows\n- used for multi-day implementation tasks\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://codedone.app/cdn/codedone-duringtask.png?v=2\" alt=\"CodeDone during task execution with backlog tickets and live agent editing\" width=\"900\"\u003e\n\u003c/p\u003e\n\n### Desktop-first experience\n\nCodeDone is built as a desktop-first application using **Go + Wails**, with a focused CLI-like workflow and support for both **dark** and **light** themes.\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://codedone.app/cdn/codedone-preview-3.png?v=2\" alt=\"CodeDone interface with theme and product UI\" width=\"900\"\u003e\n\u003c/p\u003e\n\n## Why CodeDone?\n\nMost agentic coding tools are optimized for short tasks. CodeDone is designed for long, structured, high-context development work.\n\nIt focuses on:\n\n- privacy-first local execution\n- memory safety through Go\n- atomic ticket serialization\n- lower token waste\n- higher review quality\n- direct Git-based auditability\n- configurable model/provider strategy\n- long-running autonomous project work\n\nCodeDone is for developers who want agents that can work on serious projects without turning the repository into an uncontrolled multi-agent mess.\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://codedone.app/cdn/codedone-taskcomplete.png?v=2\" alt=\"CodeDone completed task with finalizer validation\" width=\"900\"\u003e\n\u003c/p\u003e\n\n## Build\n\nCodeDone is a Wails desktop app built with Go and a web frontend.\n\nInstall the required tooling first:\n\n- Go\n- Node.js / npm\n- Wails CLI\n\nCheck your local setup:\n\n```bash\nwails doctor\n```\n\nInstall frontend dependencies if needed:\n\n```bash\nnpm install\n```\n\nBuild the app for your current operating system:\n\n```bash\nwails build\n```\n\nThe compiled app will be generated in:\n\n```text\nbuild/bin\n```\n\nFor development mode with live reload:\n\n```bash\nwails dev\n```\n\nTo build for another platform, use Wails cross-compilation support:\n\n```bash\nwails build -platform windows/amd64\nwails build -platform darwin/amd64\nwails build -platform darwin/arm64\nwails build -platform linux/amd64\n```\n\nCross-compilation can require platform-specific dependencies, so for release builds it is usually safest to build directly on the target operating system.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Finfhorus%2Fcodedone.app","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Finfhorus%2Fcodedone.app","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Finfhorus%2Fcodedone.app/lists"}