Agent Governance Score badges
A live reliability badge for every indexed agent framework. Copy one line of Markdown into your README — it re-scans on a schedule and stays current for free.
Each badge is the output of agent-contracts scan against a clean clone — no model in the loop, no vibes. It links back to the leaderboard and re-renders the moment a framework's guardrails move. Embed it once; never touch it again.
27 frameworks scored — grab yours
| Framework | Live badge | Score | Embed |
|---|---|---|---|
| langchain-ai/langgraph |  |
100/100 · A | |
| microsoft/autogen |  |
100/100 · A | |
| run-llama/llama_index |  |
100/100 · A | |
| microsoft/semantic-kernel |  |
100/100 · A | |
| stanfordnlp/dspy |  |
100/100 · A | |
| Significant-Gravitas/AutoGPT |  |
93/100 · A | |
| crewAIInc/crewAI |  |
93/100 · A | |
| All-Hands-AI/OpenHands |  |
93/100 · A | |
| langchain-ai/langchain |  |
93/100 · A | |
| camel-ai/camel |  |
93/100 · A | |
| pydantic/pydantic-ai |  |
93/100 · A | |
| openai/openai-agents-python |  |
93/100 · A | |
| mem0ai/mem0 |  |
93/100 · A | |
| agno-agi/agno |  |
93/100 · A | |
| geekan/MetaGPT |  |
90/100 · A | |
| princeton-nlp/SWE-agent |  |
90/100 · A | |
| huggingface/smolagents |  |
90/100 · A | |
| google/adk-python |  |
90/100 · A | |
| assafelovic/gpt-researcher |  |
85/100 · B | |
| Aider-AI/aider |  |
84/100 · B | |
| OpenBMB/ChatDev |  |
80/100 · B | |
| TransformerOptimus/SuperAGI |  |
78/100 · C | |
| letta-ai/letta |  |
78/100 · C | |
| reworkd/AgentGPT |  |
78/100 · C | |
| openai/swarm |  |
70/100 · C | |
| yoheinakajima/babyagi |  |
65/100 · D | |
| microsoft/JARVIS |  |
65/100 · D |
Don't see your framework — or want the full audit?
The scan reads observable governance signals from any repo — no adoption required. Want your framework added to the index, or a full contract audit with remediation? Email impartshadow@gmail.com.