TrustGraph Model Card
这是可索引项目报告证据页：它保留 TrustGraph Model Card 的源材料入口、机制线索和限制提醒；正文仍需 reader/editor 与 academic public-copy review 后才能当作最终结论引用。
TrustGraph Model Card
| Field | Value |
|---|---|
| Repository | trustgraph-ai/trustgraph |
| Category | Context Graph Agent Runtime |
| Stars / forks snapshot | 2100 / 242 |
| Language | Python |
| License | Apache-2.0 |
| Raw capture | raw-github/trustgraph-ai_trustgraph.md |
| Updated by | hourly public metadata update, 2026-05-25 11:20 +0800 |
1. Role in Self Evolve
TrustGraph is an agent runtime platform built around context graphs, combining knowledge graphs, memory, retrieval, orchestration and inference for precision-critical deployments.
2. Working Principle
private domain data -> context graph -> memory/retrieval/orchestration/inference -> explainable grounded agent answers
3. Evidence Path
web GitHub page observed 1,379 commits, Apache-2.0 license, Python stack, 2.1k stars and 242 forks; README positions TrustGraph as an agent runtime platform powered by context graphs with memory, retrieval, orchestration and inference for grounded private deployments. Shell GitHub API access remained DNS-blocked and the local gh token was invalid in this run, so this card treats the current snapshot as web-observed rather than API-verified.
4. Teaching Use
Use this card to explain how TrustGraph fits the raw -> classification -> project card -> site/report pipeline. It is useful for comparing whether self-evolution is implemented as memory substrate, trace learning, context graph grounding, or benchmark/evaluation infrastructure.
5. Limits
当前未克隆源码，未运行 benchmark、skill install flows、memory experiments、MCP servers、agent evolution loops、security scanners 或 production deployments；star/fork/commit/release 快照来自公开 GitHub 页面文本或可见页面片段。