Sign in
← Back to search
github Actively maintained

Scottcjn/legend-of-elya-n64

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.

2 awesome lists

Quick read

Stars
128
Forks
13
Open issues
3
Commits
138

Activity and growth

Latest capture 2026-08-29 03:06

Stars · last 7 days
No history
Commits · last 7 days
No history
Stars since tracking
+45
Stored snapshots
5

Classification

Topics

#ai #edge-ai #embedded-ai #game-dev #homebrew #libdragon #llm #llm-inference #machine-learning #mips #n64 #nintendo-64 #quantization #retro-gaming #retrocomputing #rustchain #tinyml #transformer #vintage-computing #zelda

Metadata

Language
C
License
MIT
Default branch
main
Created
2026-02-27
First commit
2026-02-21
Last pushed
2026-08-29
GitHub updated
2026-08-29
Last synced
2026-08-29 03:06
Stack scanned
2026-08-29 03:06
Archived
No
Sign in to like Scottcjn/legend-of-elya-n64
README Open website View on GitHub

AI development signals

0 paths

Agent instructions and tool configuration found in this repository.

No config files detected.

Growth history

Tracked growth

5 observed captures since 2026-06-12. Observed captures are shown by default.

Stars from first capture +45

Chart data

Observed captures only

Time horizon

All tracked data

Custom date range

Stars history

Observed snapshots

Commits history

Observed snapshots

Similar repositories

Nearest indexed repositories by embedding similarity.

raullenchai/Rapid-MLX

The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.

3,700 stars
Python 1 awesome list

FareedKhan-dev/kimi-k3-in-c

A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.

7,128 stars
C 1 awesome list

Mibayy/token-savior

MCP server that gets Claude to 97.9% (188/192) on a real coding benchmark at -80% active tokens and -83% wall time, vs 78.3% plain. Structural code navigation + persistent memory engine. Works with every MCP client.

1,140 stars
Python 2 awesome lists

BlinkDL/RWKV-LM

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.

14,658 stars
Python 3 awesome lists

cdeust/Cortex

Cross-platform persistent memory MCP for Codex, Gemini CLI, Claude Code, and other local MCP hosts. 36 cited neuroscience mechanisms, local-first SQLite/PostgreSQL, hybrid retrieval, decay-based consolidation, and reproducible benchmarks. Claude adds optional automatic lifecycle hooks.

72 stars
Python 1 awesome list