GraphCanon updated Sep 11, 2026 · GitHub synced Sep 11, 2026
64views this month
Decision brief
agentcanvas is for developers and AI practitioners who require detailed visual representations of Pydantic AI agent workflows, including cost breakdowns, extracted from Logfire traces.
Good fit when
- To generate interactive HTML diagrams that provide visibility into the tools, sub-agents, tokens, and costs involved in running a Pydantic AI agent.
- When assessing the exact financial implications of different components within an AI workflow executed by Pydantic agents, allowing for detailed cost analysis based on log traces.
Avoid when
- If your AI agents are not built using Pydantic or do not utilize Logfire for tracing, as agentcanvas specifically works with these technologies.
- When the level of detail provided in the HTML diagrams is unnecessary or when you lack access to the required Logfire traces and associated tokens.
Observed Jul 17, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Steady (40d since push)
- As of Sep 11, 2026
- Provenance
- Not a fork · Organization account
- As of Sep 11, 2026
- Security (OSV)
- No lockfile
- As of Jul 15, 2026
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install agentcanvasSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
Generates interactive HTML diagrams from log traces for tools, sub-agents, tokens, and cost details of Pydantic AI agents.
Capability facts
- CLI
- CLI entrypoint
Source: pyproject.toml:[project.scripts] · Sep 11, 2026
- Languages
- python
Source: github.language+pyproject.toml · Sep 11, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Sep 11, 2026)
```python from agentcanvas import LogfireClient, parse_run, render_htmlSource link
Tags
README
🚀 Quick start Set in your environment (or a file), then build the report from your latest agent run: Or use it as a library: Variable Used for reading traces via the Logfire Query API (required) optional region override (default US; EU: ) the example agent sending telemetry to L...
For agents
This page has a .md twin and JSON over the API.