{"id":51879389,"url":"https://github.com/mcamner/atlas-loop","last_synced_at":"2026-07-25T10:03:47.970Z","repository":{"id":356590193,"uuid":"1229233061","full_name":"MCamner/atlas-loop","owner":"MCamner","description":"A minimal command surface for Instagram content iteration: ideas, reels, feedback, and optimization loops.","archived":false,"fork":false,"pushed_at":"2026-06-16T09:23:34.000Z","size":58,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-06-16T11:15:37.304Z","etag":null,"topics":["ai-workflow","automation","cli","content-creation","instagram","prompts","social-media"],"latest_commit_sha":null,"homepage":"https://mcamner.github.io/atlas-loop/","language":"Shell","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/MCamner.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","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":"2026-05-04T20:48:50.000Z","updated_at":"2026-06-16T09:27:47.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/MCamner/atlas-loop","commit_stats":null,"previous_names":["mcamner/atlas-loop"],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/MCamner/atlas-loop","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MCamner%2Fatlas-loop","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MCamner%2Fatlas-loop/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MCamner%2Fatlas-loop/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MCamner%2Fatlas-loop/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/MCamner","download_url":"https://codeload.github.com/MCamner/atlas-loop/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MCamner%2Fatlas-loop/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":35875619,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-07-20T02:08:10.276Z","status":"online","status_checked_at":"2026-07-25T02:00:06.922Z","response_time":64,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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-workflow","automation","cli","content-creation","instagram","prompts","social-media"],"created_at":"2026-07-25T10:03:47.272Z","updated_at":"2026-07-25T10:03:47.960Z","avatar_url":"https://github.com/MCamner.png","language":"Shell","funding_links":[],"categories":[],"sub_categories":[],"readme":"# atlas-loop\n\nA minimal command surface for Instagram content systems.\n\nNot a tool.\nA loop.\n\n```text\nIdeas -\u003e Reels -\u003e Feedback -\u003e Iteration\n```\n\nMost people post.\nFew iterate.\n\n`atlas-loop` is built for Instagram iteration: a small product-shaped workflow\nfor turning rough ideas into Reels, captions, feedback, and better next actions.\n\n## Core Loop\n\n```text\nIDEAS -\u003e REELS -\u003e POST -\u003e ANALYZE -\u003e OPTIMIZE -\u003e REPEAT\n```\n\nThe same loop appears in the UI, CLI, prompts, and examples so the repo feels\nlike one system instead of scattered files.\n\nThe UI includes a minimal publish flow: copy content, mark it as posted, track\nInstagram metrics, analyze performance, and save each post as an experiment in\nthe local loop history.\n\n## What It Does\n\n- generates Instagram ideas from a topic\n- creates Hook Lab variants for the first 1-2 seconds of a Reel\n- turns a goal into Reel, carousel, caption, CTA, and hashtag drafts\n- critiques drafts before posting\n- improves drafts for retention, saves, shares, comments, and action\n- attaches an experiment brief: audience, pillar, hypothesis, format, metric, risk\n- tracks reach, plays, likes, saves, shares, comments, follows, and profile visits\n- calculates save, share, comment, and follow rates from reach\n- scores posts with a lightweight Signal Score\n- keeps a Next Test Queue after analysis\n- extracts winner patterns from the best saved experiments\n- stores recent posts locally so you can compare signals and repeat what works\n\n## Run The UI\n\nOpen the static app directly:\n\n```text\ndocs/index.html\n```\n\nOr serve it locally from the repo root:\n\n```bash\npython3 -m http.server 8000 --directory docs\n```\n\nThen open:\n\n```text\nhttp://127.0.0.1:8000/\n```\n\n## Run The Engine\n\nFor direct AI output, create a local `.env` file:\n\n```bash\ncp .env.example .env\n```\n\nThen edit `.env`:\n\n```text\nOPENAI_API_KEY=\"your_api_key_here\"\nOPENAI_MODEL=\"gpt-5.5\"\n```\n\nStart the engine:\n\n```bash\nnpm start\n```\n\nThen open:\n\n```text\nhttp://127.0.0.1:8787/\n```\n\nThe browser sends prompts to the local `/api/run` endpoint. The API key stays\nin the server process and is never stored in the static GitHub Pages app.\nThe `.env` file is ignored by git.\n\n## Use The CLI\n\n```bash\nchmod +x cli/atlas-loop.sh\n./cli/atlas-loop.sh ideas\n./cli/atlas-loop.sh hook\n./cli/atlas-loop.sh content\n./cli/atlas-loop.sh crit\n./cli/atlas-loop.sh optimize\n./cli/atlas-loop.sh loop\n./cli/atlas-loop.sh patterns\n```\n\nThe CLI can also fill the prompt from an argument or stdin:\n\n```bash\n./cli/atlas-loop.sh ideas \"endpoint troubleshooting for EUC operators\"\necho \"Draft caption here\" | ./cli/atlas-loop.sh crit\n```\n\n## Demo\n\n```text\n/ideas -\u003e generate Instagram ideas\n/hook -\u003e generate and compare opening hooks\n/content -\u003e create Reels, captions, and CTAs\n/crit -\u003e review draft clarity, proof, and retention\n/optimize -\u003e improve Instagram content\n/loop -\u003e analyze Instagram performance\n/patterns -\u003e extract repeatable winning patterns\n```\n\n## Structure\n\n```text\natlas-loop/\n├── README.md\n├── docs/\n│   ├── index.html\n│   ├── app.js\n│   ├── styles.css\n│   └── prompts/\n├── server.mjs\n├── package.json\n├── cli/\n│   └── atlas-loop.sh\n├── examples/\n└── LICENSE\n```\n\n## Product Position\n\nThis is not another generic social media tool.\nThis is not just another prompt repo.\n\nIt is a workflow, a mental model, and a lightweight command surface for\ncontent iteration.\n\nVersion 1 is intentionally raw:\n\n- fast\n- functional\n- readable\n- easy to extend\n\n## License\n\nMIT\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmcamner%2Fatlas-loop","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmcamner%2Fatlas-loop","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmcamner%2Fatlas-loop/lists"}