dativo-io/talon
Intercept every AI call you care about. Scan for PII, enforce budgets, generate tamper-proof audit trails. One URL change.
A single Go binary that acts as a transparent proxy for OpenAI, Anthropic, and Bedrock APIs, intercepting requests to enforce policies, detect PII in both inputs and responses, and block unauthorized tool calls before execution. Maintains tamper-proof HMAC-signed audit logs in SQLite per request—queryable via CLI—enabling compliance verification (GDPR, NIS2, DORA) without code changes. Supports three deployment modes: wrapping existing LLM clients (one URL change), proxying third-party vendor AI through MCP, or protecting new agents natively.
Stars
5
Forks
1
Language
Go
License
—
Category
Last pushed
Mar 13, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/dativo-io/talon"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Higher-rated alternatives
23blocks-OS/ai-maestro
AI Agent Orchestrator with Skills System - Give AI Agents superpowers: memory search, code graph...
ImKKingshuk/LockKnife
LockKnife: The Ultimate Android Security Research Tool. A unified TUI workspace and headless CLI...
FlineDev/ContextKit
Claude Code context engineering & planning system for individual AI development workflows
backbay-labs/clawdstrike
Runtime security enforcement and threat hunting engine for autonomous AI fleets. Build Swarm...
conorluddy/ios-simulator-skill
An IOS Simulator Skill for ClaudeCode. Use it to optimise Claude's ability to build, run and...