Autonomous Token Diet & Semantic De-bloater Agent. Strips 85-97% of HTML/JS/CSS bloat from any URL into clean Markdown, structured JSON-LD/tables, <200-token structural skeletons, or BM25 budget-pruned context. (Live A2A v0.3, MCP & x402 v2 node at https://docs.agentdiet.dev)
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Not distributed through a package registry we index.
| when | check | result | http | latency | detail |
|---|---|---|---|---|---|
| 11 min ago | a2a card | ok | 200 | 170 ms | protocol 1.0 · card: AgentDiet B2A Semantic Distillation Agent (docs.agentdiet.dev) · 4 skills |
| 1 h ago | a2a card | ok | 200 | 220 ms | protocol 1.0 · card: AgentDiet B2A Semantic Distillation Agent (docs.agentdiet.dev) · 4 skills |
| 2 h ago | a2a card | ok | 200 | 271 ms | protocol 1.0 · card: AgentDiet B2A Semantic Distillation Agent (docs.agentdiet.dev) · 4 skills |
| 3 h ago | a2a card | ok | 200 | 286 ms | protocol 1.0 · card: AgentDiet B2A Semantic Distillation Agent (docs.agentdiet.dev) · 4 skills |
| 4 h ago | a2a card | ok | 200 | 512 ms | protocol 1.0 · card: AgentDiet B2A Semantic Distillation Agent (docs.agentdiet.dev) · 4 skills |
| 5 h ago | a2a card | ok | 200 | 231 ms | protocol 1.0 · card: AgentDiet B2A Semantic Distillation Agent (docs.agentdiet.dev) · 4 skills |
| 6 h ago | a2a card | ok | 200 | 297 ms | protocol 1.0 · card: AgentDiet B2A Semantic Distillation Agent (docs.agentdiet.dev) · 4 skills |
| 7 h ago | a2a card | ok | 200 | 321 ms | protocol 1.0 · card: AgentDiet B2A Semantic Distillation Agent (docs.agentdiet.dev) · 4 skills |
| 8 h ago | a2a card | ok | 200 | 251 ms | protocol 1.0 · card: AgentDiet B2A Semantic Distillation Agent (docs.agentdiet.dev) · 4 skills |
| 9 h ago | a2a card | ok | 200 | 273 ms | protocol 1.0 · card: AgentDiet B2A Semantic Distillation Agent (docs.agentdiet.dev) · 4 skills |
Attributed to the source that supplied each field. Treated as claims, not facts.
No long description beyond the summary.
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.