Search
@glideco/skill-ap-agent-claude-quickbooks
darshanbathija
AP agent skill for Claude Desktop + QuickBooks Online — drafts vendor payments from QBO invoices within a policy envelope, queues them for principal approval.
...more@glideco/skill-trip-budget-chatgpt
darshanbathija
Trip-budget skill for ChatGPT — issues a scoped virtual card for a weekend with MCC filters + auto-revoke.
karotte
Let an LLM execute tasks in an environment.
comuvia
Comuvia
Offline, provider-neutral evidence and prediction records: validation, canonical identity, append-only storage and binary evaluation.
...moreajisai-mcp-server
masamoto
Temporary package placeholder for staged publishing
tuieval
tuieval contributors
Evaluate local LLMs on your own eval packs, in the terminal: accuracy, speed and tokens, with PASS/FAIL verdicts.
routemark
Saar Inc.
Let Claude Code or Codex hand execution work to a cheaper coding agent on your machine, review it, and merge exactly what passed.
...more@privacyscrubber/fastmcp-guard
privacyscrubber
Temporary package placeholder for staged publishing
@ponsmcp/sdk
ponsmcp
PonsMCP SDK + MCP server - autonomous agent payments (MPP) settled in USDG on Robinhood Chain 4663, with pons launch intelligence tools.
...moreboruna
escapeboy
Boruna: a deterministic, capability-safe programming language and framework for LLM-native applications