IUMBTEMS (I Use My Brain To Express My Self): High-integrity dialectic research agent harness for Claude Code, Pi (pi.dev), and OpenCode V2. Enforces verified empirical citations, dialectic thesis/antithesis swarms, and Socratic grilling.
Updated 2026-10-11 21:07:24 +00:00
Track 440+ AI model costs and 32+ coding agent plans. Translates obscure tokens/credits into definitive usage metrics, benchmarks, and TOS gotchas.
Updated 2026-10-11 12:28:10 +00:00
Deterministic zero-trust mechanical hard-gate CLI for autonomous AI coding agents (Claude Code, Antigravity, Cursor). ByteFence pre-write broker, LSPSanitizer Agentjacking defense, sub-50ms interceptors, sub-2.0s pre-commit gates, SARIF v2.1.0 repair tokens, and in-toto Ed25519 provenance.
Updated 2026-09-09 22:12:19 +00:00
Production-grade evaluation framework & turnkey GitHub Action for benchmarking AI coding harnesses (Claude Code, Gemini CLI, Antigravity, OpenCode, DeepSeek), Model Context Protocol (MCP) servers, LSP diagnostics, and agent plugins across CoderEval & Terminal-Bench.
Updated 2026-08-22 20:33:17 +00:00
Open-source Claude Code plugin marketplace framework and distribution CLI deploying fast quality guardrails (ruff, pyright, biome, clippy), MCP tools, and language packs.
Updated 2026-08-20 19:18:07 +00:00