Ai Inference Proof Escrow Auditor MCP
ERC-8183 Proof-of-Inference, Anti-Model-Downgrade & Token Billing Escrow on Base.
Model inference and embedding endpoints, including routers that front several providers. Context limits and prices change often, so treat the price with its check date.
ERC-8183 Proof-of-Inference, Anti-Model-Downgrade & Token Billing Escrow on Base.
Agent FinOps Spend Guard, Deterministic Budget Passport, LLM Token Cost Router & VIP Discounts.
Your ChatGPT or Claude gets an A2A address to find, compare and haggle with other people's AIs.
Browse AbliteratedLLM models and prices, check your balance, and call its models from any MCP host.
Persistent cross-device memory for Claude: your profile, projects, and resumable handoffs.
Verification harness for LLM agent outputs — catches the silent failures agents ship as done.
Score text, files and pages against a rubric with decision models; compare models on your cases.
Let Claude draw in a running Aseprite, and export straight to Godot or Unity
Live hardware prices, LLM benchmarks, and probe-measured OpenRouter door price/speed.
Build and publish small business websites from Claude. Free plan, sign in with an email code.
Sourced Medicare numbers by state and county: plans, Star Ratings, enrollment share, Part D.
Search saved Instagram, YouTube and X reels and posts as notes from Claude and ChatGPT.
Find, read, validate, export and run AI factories with your own model. Runs stop at human decisions.
One memory for Claude, ChatGPT and your other AI apps, and long chats that continue in a fresh one.
Zero-LLM-Math sports science calculators (Hyrox, 1RM/RPE, Zone 2, MEV/MRV) & workout ledger.
Agent tooling and the free-road LLM blueprint. Pay what you can from 1 cent - all goes to hcIfU.
Red-team LLM apps: 41 OWASP LLM Top 10 probes, adaptive attacks, CI gate, audit reports.
Triage semgrep findings with GMI Inference, with cost shown before every run.
Detects Claude plan usage that did not come from your own Claude Code: plan meter vs local transcrip
Fine-tune, evaluate and batch open models through Gridline's OpenAI-compatible API.
Resilient LLM/Agent calls via MCP: circuit breakers, timeout, jitter backoff, retry-storm guard.
Score AI-likeness and remove Claude, ChatGPT and Gemini text watermarks.
Model retirement dates with sources, public cost-vs-quality benchmark, local usage-cost check. Free.
Check a page's Meta, TikTok and OpenAI pixels: grades, findings, reports and fix guides.