{"data":{"slug":"agi-merge-waggle-dance","name":"waggle-dance","tagline":"Knowledge work automation with AI agents","github_url":"https://github.com/agi-merge/waggle-dance","owner":"agi-merge","repo":"waggle-dance","owner_avatar_url":"https://avatars.githubusercontent.com/u/131612568?v=4","primary_language":"TypeScript","stars":171,"forks":12,"topics":["agent","agent-based-framework","ai","autogpt","langchain","langchain-js","llm","nextjs","openai","weaviate","workflow-automation"],"archived":true,"github_pushed_at":"2023-12-17T23:18:51+00:00","maintenance_label":"Archived","stars_delta_30d":0,"url":"https://www.graphcanon.com/tools/agi-merge-waggle-dance","markdown_url":"https://www.graphcanon.com/tools/agi-merge-waggle-dance.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/agi-merge-waggle-dance","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=agi-merge-waggle-dance","description":"Knowledge work automation with AI agents","homepage_url":"https://waggledance.ai","license":"MIT","open_issues":0,"watchers":3,"ai_summary":"Automates knowledge work using an agent-based framework that includes Planner Agents, Execution Agents, and Criticism Agents to achieve user-specified goals.","readme_excerpt":"## Quick Start\n\n- Try the cloud preview ↗\n- [Join the Discord](https://discord.gg/ttt9YmhQU6)\n- ⭐️ Help with algorithm: star this repo\n\nYou can also build and deploy yourself! However, [you must configure your environment](#%EF%B8%8F-configure-your-environment).\n\n- Deploy to Vercel\n- [Docker Compose](#-docker)\n- [Build and run from source](#-running-locally-and-development)\n\n**waggledance.ai** is an experimental application focused on achieving user-specified goals. It provides a friendly but opinionated user interface for building agent-based systems. The project focuses on explainability, observability, concurrent generation, and exploration. Currently in pre-alpha, the development philosophy prefers experimentation over stability as goal-solving and Agent systems are rapidly evolving.\n\nwaggledance.ai takes a goal and passes it to a **Planner Agent** which streams an execution graph for sub-tasks. Each sub-task is executed as concurrently as possible by **Execution Agents**. To reduce poor results and hallucinations, sub-results are reviewed by **Criticism Agents**. Eventually, the **Human in the loop (you!)** will be able to chat with individual Agents and provide course-corrections if needed.\n\nIt was originally inspired by [Auto-GPT](https://github.com/Significant-Gravitas/Auto-GPT), and has concurrency features similar to those found in [gpt-researcher](https://github.com/assafelovic/gpt-researcher). Therefore, core tenets of the project include _speed_, _accuracy_, _observability_, and _simplicity_. Additionally, many other agentic systems are written in Python, so this project acts as a small counter-balance, and is accessible to the large number of Javascript developers.\n\nAn (unstable) API is also available via [tRPC](packages/api/src/root.ts) as well an API [implemented within Next.js](apps/nextjs/src/pages/api). The client-side is mostly responsible for orchestrating and rendering the agent executions, while the API and server-side executes the agents and stores the results. This architecture is likely to be adjusted in the future.\n\n

\n\n\n \n \n \"bar\"\n\n\n

\n","github_created_at":"2023-04-23T17:55:09+00:00","created_at":"2026-07-11T10:47:35.850742+00:00","updated_at":"2026-08-15T00:01:29.823896+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"agent","name":"agent"},{"slug":"autogpt","name":"autogpt"},{"slug":"langchain","name":"langchain"},{"slug":"weaviate","name":"weaviate"},{"slug":"workflow-automation","name":"workflow-automation"}],"trust":{"provenance":{"is_fork":false,"github_id":631656598,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-15T00:01:28.608Z","maintenance":{"label":"Archived","score":8,"methodology":"github_public_v1","releases_90d":0,"days_since_push":971,"last_release_at":null,"stars_delta_30d":0,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T10:47:37.351Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"mcp":{"source":"repo_scan","observed_at":"2026-08-15T00:01:29.180Z","server_manifest":false},"scan":{"source":"repo_scan","observed_at":"2026-08-15T00:01:29.180Z"},"deploy":{"source":"dockerfile:Dockerfile","self_host":true,"observed_at":"2026-08-15T00:01:29.180Z","managed_saas":false},"has_cli":{"value":true,"source":"package.json:bin|scripts","observed_at":"2026-08-15T00:01:29.180Z"},"languages":{"value":["typescript","javascript"],"source":"github.language+package.json","observed_at":"2026-08-15T00:01:29.180Z"},"has_docker":{"value":true,"source":"dockerfile:Dockerfile","observed_at":"2026-08-15T00:01:29.180Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-08-15T00:01:29.180Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["You need a system that prioritizes speed and concurrency in executing tasks","You prefer a TypeScript project over Python alternatives in the same category"],"when_not_to_use":["Your project demands high stability over experimental features","You require extensive customization of agent execution behavior beyond what Waggle-dance offers initially"],"source":"enrich:decision_facts","observed_at":"2026-07-14T19:55:39.350Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Waggle-dance is an AI-driven knowledge work automation tool built in TypeScript with experimental concurrent agent execution for faster task resolution."}]}}