v1.0.1 · no license
Enables AI assistants to look up, create, update, archive, pause and resume short links and QR codes, and to read account, link and QR code click analytics, with every change reversible and nothing permanently deleted. It is a hosted, OAuth-authenticated remote server that requires no installation.
v1.5.271 · Apache 2.0
Let Claude Code, Codex and any AI agent use the Chrome you're already signed in to. Open-source CLI + MCP server + Chrome extension (native messaging, no debug port); stealth by default.
v1.0.0 · MIT License
Encode, decode, and convert numbers across FP64, FP32, FP16, BF16, TF32, OCP FP8/FP6/FP4, MX, and integer formats, with bit-level breakdowns, rounding modes, and precision-loss analysis. Runs locally; no API key needed.
v3.60.0 · MIT License
Thea Software is an engineering verification layer for AI agents that binds code changes to explicit validation commands. It bridges conversational models to robust software runtimes, enforcing automated build checks so that code drift and unverified changes are actively rejected.
v0.6.0 · MIT License
Session-level (not fragment) local memory for AI coding agents: passively captures Claude Code, Codex, ZCode and Qoder conversations into one SQLite store, with provenance-cited retrieval and a human-only right to be forgotten.
— · MIT License
Lets AI agents turn a UPI QR code plus cart details into a single review-and-pay page link that opens GPay, PhonePe or Paytm pre-filled, so a human pays in one tap. Agents can also poll live payment status and set or confirm it, closing the checkout loop with signed webhooks.
v0.4.6 · Apache 2.0
Inventory local Codex plugins and Skills, inspect recorded usage, and identify potential redundancy to support user-directed cleanup. Includes a local MCP service, dashboard, and companion Skills; requires Windows and a local Codex environment.
v1.1.1 · MIT License
Enables Cursor and Codex agents to audit Agent Skill structure (frontmatter, broken links, missing files), analyze dependencies for undeclared, unused or vulnerable packages via OSV, and run 28 local bug and code-quality rules with SonarQube-style A–E ratings. It can also optionally pull issues, metrics and quality-gate status from SonarQube or SonarCloud, or scan and upload results.