Live browser sessions for AI agents
MCP server: structured-output enforcer. Extract JSON from messy LLM output, validate against a shape spec, and produce retry feedback when the model returns the wrong shape. Wraps @mukundakatta/agentcast.
Structured output for any LLM call. Validate the model's response, retry with the validation error as feedback, return typed data or throw after N attempts. Bring your own validator (zod/valibot/JSON Schema/anything). Zero deps.
The agent reliability stack: fit, guard, snap, vet, cast. One install for all five sibling libraries (token-aware truncation, network-egress firewall, snapshot tests, tool-arg validation, structured-output enforcer).
Replay AI agent CLI sessions (Claude Code, Gemini CLI, Copilot CLI) for demos and presentations
Structured-output enforcer for LLM responses. Repair + validate + (optional) retry-with-LLM. BYO-LLM, BYO-schema.
Fuzzy-match LLM-generated args to JSON Schema enum values. Zero-Levenshtein cascade (exact / case-insensitive / prefix / substring) with ambiguity guard. coerce_enums rewrites enum-constrained string properties before strict validation.