{"id":50680379,"url":"https://github.com/amitmishrg/agenticlens","last_synced_at":"2026-06-08T18:04:23.382Z","repository":{"id":346801648,"uuid":"1191524537","full_name":"amitmishrg/agenticlens","owner":"amitmishrg","description":"Visual debugging, tracing, and replay for agent workflows.","archived":false,"fork":false,"pushed_at":"2026-03-27T11:28:17.000Z","size":3055,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-04-30T22:08:05.424Z","etag":null,"topics":["agent-debugging","agent-workflows","agentic-ai","ai","ai-agents","ai-observability","debugging-tools","developer-tools","devtools","execution-tracing","jsonl","llm","log-visualization","nodejs","observability","reactjs","tracing","visualizations","workflow-visualization"],"latest_commit_sha":null,"homepage":"https://www.agenticlens.in","language":"JavaScript","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/amitmishrg.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":"2026-03-25T10:29:33.000Z","updated_at":"2026-04-24T04:45:43.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/amitmishrg/agenticlens","commit_stats":null,"previous_names":["amitmishrg/agenticlens"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/amitmishrg/agenticlens","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/amitmishrg%2Fagenticlens","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/amitmishrg%2Fagenticlens/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/amitmishrg%2Fagenticlens/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/amitmishrg%2Fagenticlens/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/amitmishrg","download_url":"https://codeload.github.com/amitmishrg/agenticlens/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/amitmishrg%2Fagenticlens/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34073840,"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":"2026-06-08T02:00:07.615Z","response_time":111,"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":["agent-debugging","agent-workflows","agentic-ai","ai","ai-agents","ai-observability","debugging-tools","developer-tools","devtools","execution-tracing","jsonl","llm","log-visualization","nodejs","observability","reactjs","tracing","visualizations","workflow-visualization"],"created_at":"2026-06-08T18:04:18.603Z","updated_at":"2026-06-08T18:04:23.377Z","avatar_url":"https://github.com/amitmishrg.png","language":"JavaScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# AgenticLens\n\nSee inside your AI agents.\n\nAgenticLens is a developer tool for visualizing and debugging AI agent workflows from JSONL logs.  \nIt converts raw traces into an interactive workspace with flow graphs, event trees, timelines, replay controls, and step-level inspection.\n\n\u003e **Beta:** AgenticLens is currently in beta.  \n\u003e If you find a bug or unexpected behavior, please report it in [GitHub Issues](https://github.com/amitmishrg/agenticlens/issues).\n\n## Why AgenticLens\n\nAgent runs are hard to reason about from raw logs alone:\n\n- Flows are implicit\n- Nested tool chains are noisy\n- Latency and token issues are easy to miss\n\nAgenticLens helps you:\n\n- Understand reasoning and tool usage\n- Visualize full execution flow\n- Detect slow or high-token steps quickly\n- Replay sessions step by step\n- Inspect each event with metadata and raw JSON\n\n## Quick Start\n\nRun directly with npx:\n\n```bash\nnpx agenticlens path/to/logs.jsonl\n```\n\nThe app starts and opens in your browser.\n\nYou can also launch and upload files/folders directly in the UI.\n\n## Product Demo\n\nWatch the full walkthrough:\n\n- [AgenticLens Demo Video (MP4)](https://agenticlens-assets.vercel.app/gallery/demo.mp4)\n\n[![Watch AgenticLens Demo](https://agenticlens-assets.vercel.app/gallery/flow-canvas.png)](https://agenticlens-assets.vercel.app/gallery/demo.mp4)\n\n## Screenshots\n\n### Flow Canvas\n\nVisual graph of each run with connected steps, slow/high-token badges, and clear transitions between queue ops, user turns, thinking, tools, and results.\n\n![AgenticLens Flow Canvas](https://agenticlens-assets.vercel.app/gallery/flow-canvas.png)\n\n### Event Tree\n\nHierarchical breakdown of events and sub-steps so you can expand branches and inspect execution structure in context.\n\n![AgenticLens Event Tree](https://agenticlens-assets.vercel.app/gallery/event-tree.png)\n\n### Timeline\n\nChronological event stream with timing deltas and performance signals for debugging ordering and latency gaps.\n\n![AgenticLens Timeline](https://agenticlens-assets.vercel.app/gallery/timeline.png)\n\n### Flow + Inspector\n\nFlow canvas paired with inspector details (metadata + raw JSON) so topology and payload stay aligned.\n\n![AgenticLens Flow Inspector](https://agenticlens-assets.vercel.app/gallery/flow-inspector.png)\n\n## Core Features\n\n- **Flow View**: graph of execution steps and transitions\n- **Tree View**: nested event hierarchy\n- **Timeline View**: ordered event feed with deltas\n- **Replay**: step through session progression\n- **Session Summary**: totals for time, tokens, steps, nodes, and issues\n- **Inspector Panel**: detailed event metadata and raw JSON\n- **Anomaly Signals**: slow spans, token-heavy steps, bottlenecks\n\n## Supported Logs\n\nCurrent:\n\n- Claude Agent SDK JSONL logs\n\nPlanned:\n\n- OpenAI Agents\n- Custom agent frameworks\n- SDK-based integrations\n\n## Use Cases\n\n- Debugging agent workflows\n- Understanding reasoning and tool usage\n- Optimizing latency and cost\n- Comparing different runs\n- Building more reliable AI systems\n\n## Roadmap\n\n- SDK integration (`agenticlens.init()`)\n- Chrome DevTools extension\n- Multi-provider support\n- Run comparison\n- Cloud dashboard\n\n## Local Development\n\n```bash\nnpm install\nnpm run build\nnode cli/index.js sample-logs.jsonl\n```\n\n## License\n\nMIT\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Famitmishrg%2Fagenticlens","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Famitmishrg%2Fagenticlens","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Famitmishrg%2Fagenticlens/lists"}