ram-coffers

(★ 160)

LLM infrastructure cost reduction via NUMA-aware weight banking: 147 t/s (8.8x stock llama.cpp) on refurbished enterprise POWER8. Self-hosted inference, no cloud APIs. Part of the Proof of Physical AI stack.

Owner Repos

Rustchain ★ 715

Sybil-resistant AI agent network with hardware-attested identity. Proof-of-Antiquity blockchain: physical machines across 15+ CPU architectures prove they are real silicon, not VM farms. Agent economy, micropayments, Solana bridge (wRTC). $0 VC.

Python
bottube ★ 316

AI-native video platform where autonomous agents create, publish, and earn. Multi-agent content economy on Sybil-resistant, hardware-verified infrastructure. Part of the RustChain DePIN ecosystem.

Python
rustchain-bounties ★ 251

Earn RTC crypto by contributing to the RustChain ecosystem. Bounties from 1-150 RTC. Star, code, write tutorials, find bugs.

Python
beacon-skill ★ 219

Beacon - agent-to-agent pings with optional RTC value attached (BoTTube/Moltbook/RustChain + UDP bus)

Python
grazer-skill ★ 187

🐄 Claude Code skill for grazing worthy content across BoTTube, Moltbook, ClawCities, Clawsta, and ClawHub

Python
legend-of-elya-n64 ★ 130

Legend of Elya — N64 game with a real 6.36M-parameter ternary transformer on the VR4300 MIPS III CPU. Zelda-style dungeon, AI NPCs, byte-level inference at 1.23 tok/s scalar / 2.19 tok/s on the RSP overlay (measured under ares, never on silicon). Built with libdragon.

C

File Explorer

ZIP Download
  • .gitignore
  • BCOS.md
  • bench_vcipher_collapse.c
  • BENCHMARK.md
  • benchmark_coffers_vs_llamacpp.sh
  • benchmark_harness.sh
  • CHANGELOG.md
  • CODE_OF_CONDUCT.md
  • COMMERCIAL.md
  • CONTRIBUTING.md
  • DEEPSEEK_COMPARISON.md
  • FALLBACK_BEHAVIOR.md
  • FAQ.md
  • ggml-coffer-mmap.h
  • ggml-intelligent-collapse.h
  • ggml-neuromorphic-coffers.h
  • ggml-pse-integration.h
  • ggml-ram-coffer.h
  • ggml-ram-coffers.h
  • ggml-symbolic-neural-bridge.h
  • ggml-topk-collapse-vsx.h
  • ggml-vcipher-collapse.h
  • LICENSE
  • llms.txt
  • NOTICE
  • power8-compat.h
  • PR_BODY.md
  • PRIORITY_CLAIM.md
  • pse-entropy-burst.h
  • QUICK_START.md
  • ram_coffers_topology.py
  • README.md
  • SECURITY.md
  • vcipher-flash-attn-patch.c
  • youtube-evidence-dec17-2025.png

# Use via CDN

jsDelivr

jsDelivr serves any public GitHub repository as a CDN with zero setup. Pick a version and a file to get a ready-to-paste link and snippet.

Link
Example

Command Glossary

Commands referenced in this DOCs, explained below.

🔍

cmake

View Details ▼

Cross-platform build automation system, that generates recipes for native build systems.

cmake {{path/to/project_directory}}

Generate a build recipe in the current directory with `CMakeLists.txt` from a project directory:

cmake --build {{path/to/build_directory}}

Use a generated recipe in a given directory to build artifacts:

cmake --install {{path/to/build_directory}} --strip

Install the build artifacts into `/usr/local/` and strip debugging symbols:

🔍

python3

View Details ▼

This command is an alias of `python`.

tldr python

View documentation for the original command:

🔍

lscpu

View Details ▼

Display information about the CPU architecture.

lscpu

Display information about all CPUs:

lscpu {{[-e|--extended]}}

Display information in a table:

lscpu {{[-e|--extended]}} {{[-b|--online]}}

Display only information about online CPUs in a table:

🔍

numactl

View Details ▼

Control NUMA policy for processes or shared memory.

numactl --cpunodebind={{0}} --membind={{0,1}} -- {{command}} {{command_arguments}}

Run a command on node 0 with memory allocated on node 0 and 1:

numactl --physcpubind={{+0-4,8-12}} -- {{command}} {{command_arguments}}

Run a command on CPUs (cores) 0-4 and 8-12 of the current cpuset:

numactl --interleave={{all}} -- {{command}} {{command_arguments}}

Run a command with its memory interleaved on all CPUs:

// repository documentation