{"id":50697436,"url":"https://github.com/oskarrough/llmlake","last_synced_at":"2026-06-09T07:32:53.744Z","repository":{"id":360956734,"uuid":"1235560742","full_name":"oskarrough/llmlake","owner":"oskarrough","description":null,"archived":false,"fork":false,"pushed_at":"2026-05-28T15:12:27.000Z","size":169,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-05-28T16:22:30.633Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/oskarrough.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2026-05-11T12:48:36.000Z","updated_at":"2026-05-28T15:18:26.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/oskarrough/llmlake","commit_stats":null,"previous_names":["oskarrough/llmlake"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/oskarrough/llmlake","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/oskarrough%2Fllmlake","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/oskarrough%2Fllmlake/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/oskarrough%2Fllmlake/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/oskarrough%2Fllmlake/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/oskarrough","download_url":"https://codeload.github.com/oskarrough/llmlake/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/oskarrough%2Fllmlake/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34096950,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-09T02:00:06.510Z","response_time":63,"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":[],"created_at":"2026-06-09T07:32:53.245Z","updated_at":"2026-06-09T07:32:53.733Z","avatar_url":"https://github.com/oskarrough.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# llmlake\n\nA local tool that helps you learn from your (possibly many) LLM sessions across agents (Claude Code, Pi, Codex, Hermes): it transforms the raw session files into denormalized .parquet files you can query with DuckDB and turn into (HTML) insights using installable agent skills.\n\n```\n  ~/.claude  ~/.codex  ~/.pi  ~/.hermes\n      └──────────┴──┬───┴─────────┘\n                    ▼\n                 collect → data/sessions (↔ optional rsync)\n                    │\n                    ▼\n                 build → data/parquet\n                    │\n         ┌──────────┴──────────┐\n       query               ai skills\n       (SQL)            (HTML insights)\n```\n\n---\n\nInstall [Duckdb](https://duckdb.org/install/) and `git clone https://github.com/oskarrough/llmlake`.\n\nInstall the skills into any supported coding agent:\n\n```sh\nbunx skills add oskarrough/llmlake\n```\n\nOnce inside the cloned repo, you can _collect_ sessions, _build_ them into .parquet files, _query_ the DB with SQL.\n\n`./llmlake collect`\n\nMoves all raw session files from your local computer into `./data/sessions`. The `data` folder is gitignored.\n\n`./llmlake build`\n\nTransforms them into parquet files inside `data/parquet`.\n\n```sh\n./llmlake query -c \"SELECT session_id, count(*) FROM events WHERE agent='pi' GROUP BY 1 ORDER BY 2 DESC LIMIT 10;\"\n```\n\nQuery the parquet with duckdb (or ask your agent to do it)\n\n`./llmlake sync \u003cpath\u003e`\n\nBonus feature: two-way rsync between `data/sessions/` and a shared folder, so multiple devices share one library. For example, I use it to store my data in dropbox: `./llmlake sync ~/Dropbox/my-ai-sessions`.\n\n## Skills\n\nAfter `collect` and `build`, open any coding agent with skills support in this repo and run one of these:\n\n- `llmlake:explore-lake` — ask questions about sessions, costs, tools, models, projects, or activity patterns.\n- `llmlake:generate-insights` — create an HTML report for a period, such as last week, last month, or all time.\n- `llmlake:inspect-session` — create a focused HTML deep-dive for one session id.\n\n## File overview for contributors\n\n- `collect-{claude,codex,hermes, pi}` — copy sessions\n- `build` — parse every collected JSONL file into parquet \n- `build-one` — parse a single raw JSONL file into parquet\n- `query` — duckdb shell over `data/parquet/` with an `events` view\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Foskarrough%2Fllmlake","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Foskarrough%2Fllmlake","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Foskarrough%2Fllmlake/lists"}