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.
ai-agents
autonomous-agents
citation-validation
claude-code
cli
deep-research
dialectic
epistemic-integrity
fact-checking
hallucination-prevention
mcp-servers
model-context-protocol
multi-agent-systems
opencode
opencode-plugin
pi-package
red-teaming
research-agent
socratic-questioning
swarm-intelligence
Updated 2026-10-11 21:07:24 +00:00
Updated 2026-10-11 20:59:43 +00:00
Updated 2026-10-11 20:59:39 +00:00
Updated 2026-10-11 20:59:39 +00:00
Updated 2026-10-11 20:59:38 +00:00
Updated 2026-10-11 20:59:32 +00:00
Updated 2026-10-11 20:51:37 +00:00
Updated 2026-10-11 20:49:59 +00:00
Updated 2026-10-11 20:49:58 +00:00
Updated 2026-10-11 20:49:55 +00:00
⚡ Zero-dependency Homebrew tap for high-performance LLMs (CachyLLama, ROCmFPX, llama-ai). Optimized for AMD ROCm 7 (Strix Halo, RDNA3/4), Apple Silicon Metal, & Vulkan RADV.
ai-inference
amd-gpu
apple-silicon
cachy-llama
homebrew
homebrew-tap
inference
llama-cpp
llm
local-ai
metal
quantization
rdna3
rdna4
rocm
rocm-gpu
rocmfpx
strix-halo
strix-point
vulkan-radv
Updated 2026-10-11 20:01:07 +00:00
Track 440+ AI model costs and 32+ coding agent plans. Translates obscure tokens/credits into definitive usage metrics, benchmarks, and TOS gotchas.
ai-models
artificial-analysis
benchmarks
claude-code
coding-agents
copilot
cursor
developer-tools
llm-pricing
openrouter
price-tracker
react
swe-bench
tailwind
token-cost-calculator
vite
Updated 2026-10-11 12:28:10 +00:00
Updated 2026-10-10 22:27:25 +00:00