{"data":{"slug":"lavague-ai-lavague","name":"LaVague","tagline":"Large Action Model framework to develop AI Web Agents","github_url":"https://github.com/lavague-ai/LaVague","owner":"lavague-ai","repo":"LaVague","owner_avatar_url":"https://avatars.githubusercontent.com/u/163125966?v=4","primary_language":"Python","stars":6386,"forks":573,"topics":["ai","browser","large-action-model","llm","oss","rag"],"archived":false,"github_pushed_at":"2025-01-21T13:41:48+00:00","maintenance_label":"Dormant","stars_delta_30d":6,"url":"https://www.graphcanon.com/tools/lavague-ai-lavague","markdown_url":"https://www.graphcanon.com/tools/lavague-ai-lavague.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/lavague-ai-lavague","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=lavague-ai-lavague","description":"Large Action Model framework to develop AI Web Agents","homepage_url":"https://docs.lavague.ai/en/latest/","license":"Apache-2.0","open_issues":104,"watchers":53,"ai_summary":"LaVague is a framework for developing AI web agents using Large Language Models (LLMs). It supports customization of LLMs and tracking of token usage for cost estimation.","readme_excerpt":"## 💰 How much does it cost to run an agent?\n\nLaVague uses LLMs, (by default OpenAI's `gpt4-o` but this is completely customizable), under the hood.\n\nThe cost of these LLM calls depends on: \n- the models chosen to run a given agent\n- the complexity of the objective\n- the website you're interacting with. \n\nPlease see our [dedicated documentation on token counting and cost estimations](https://docs.lavague.ai/en/latest/docs/get-started/token-usage/) to learn how you can track all tokens and estimate costs for running your agents.","github_created_at":"2024-02-26T23:40:23+00:00","created_at":"2026-07-07T17:37:38.928688+00:00","updated_at":"2026-08-18T18:01:02.942791+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"}],"tags":[{"slug":"ai","name":"ai"},{"slug":"browser","name":"browser"},{"slug":"large-action-model","name":"large-action-model"},{"slug":"llm","name":"llm"},{"slug":"oss","name":"oss"},{"slug":"rag","name":"rag"}],"trust":{"provenance":{"is_fork":false,"github_id":763795053,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-18T18:01:01.460Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":574,"last_release_at":null,"stars_delta_30d":6,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:10:10.594Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-18T18:01:02.581Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-08-18T18:01:02.581Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-08-18T18:01:02.581Z"}},"decision_facts":{"hosting":null,"pricing":{"model":"freemium","summary":"Free to use with customizable LLMs; actual costs depend on the specific LLM used and operational complexity."},"requirements":{"notes":["Requires Python for development."],"min_ram_gb":2},"constraints":{"min_ram_gb":2,"pricing_model":"freemium"},"when_to_use":["When you need a flexible framework that allows customization of LLMs, particularly if your primary model is OpenAI's `gpt4-o` or similar models.","If your project involves interacting with various websites requiring different levels of LLM complexity and you want precise cost estimation for running your agents."],"when_not_to_use":["Avoid using LaVague if you are working on projects that do not involve AI web agent development, as the framework is specifically designed around this use-case.","Do not opt for LaVague if you require a non-Python environment for your development since the framework is Python-based."],"source":"enrich:decision_facts","observed_at":"2026-07-12T16:10:38.835Z"},"constraint_facets":{"min_ram_gb":2,"pricing_model":"freemium"},"decision_summary":[{"label":"Pricing","value":"freemium - Free to use with customizable LLMs; actual costs depend on the specific LLM used and operational complexity."},{"label":"Requirements","value":"Min 2 GB RAM; Requires Python for development."},{"label":"Adopt for","value":"Large Action Model (LaVague) framework supports developing AI web agents using customizable Large Language Models (LLMs), offering tracking of token usage for cost estimation purposes."},{"label":"License detail","value":"LaVague's license (Apache-2.0) allows free use in both open and closed-source applications, provided that copyright notices are preserved."}]}}