GraphCanon updated today · GitHub synced today · 31 views this month
Decision brief
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.
Good fit when
- 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.
Avoid when
- 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.
- Pricing:
- freemium - Free to use with customizable LLMs; actual costs depend on the specific LLM used and operational complexity.
- Requirements:
- Min 2 GB RAM; Requires Python for development.
Observed Jul 12, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Dormant (574d since push)
- As of today
- Provenance
- Not a fork · Organization account
- As of today
- Security (OSV)
- No lockfile
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install LaVagueHow it fits your stack(5)
Typed graph edges - alternatives, integrations, successors, and dependencies. Ranked by relationship type, not raw GitHub stars.
Integrates
Relationship graph
Optional deeper exploration of typed edges and category neighbours.
Similar tools
Same-category neighbours not already linked as typed edges.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
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.
Capability facts
- Languages
- python
Source: github.language+pyproject.toml · Aug 18, 2026
Categories
Graph entities
Tags
README
💰 How much does it cost to run an agent?
LaVague uses LLMs, (by default OpenAI's gpt4-o but this is completely customizable), under the hood.
The cost of these LLM calls depends on:
- the models chosen to run a given agent
- the complexity of the objective
- the website you're interacting with.
Please see our dedicated documentation on token counting and cost estimations to learn how you can track all tokens and estimate costs for running your agents.
For agents
This page has a .md twin and JSON over the API.