microGPT benchmarks: a single M4 Max MacBook Pro P-core in C runs Karpathy's 4192-parameter transformer at ~71x the throughput of TALOS-V2's FPGA implementation.
☆165May 4, 2026Updated 4 months ago
Alternatives and similar repositories for talos-vs-macbook
Users that are interested in talos-vs-macbook are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- hardware implementation of transformers running microgpt at 50k+ tkps☆776May 14, 2026Updated 4 months ago
- ☆122May 5, 2026Updated 4 months ago
- ☆18May 23, 2026Updated 3 months ago
- Agent memory infrastructure: provenance, rollback, lifecycle/supersession, three-layer model (working memory + session archive + wiki). M…☆291May 8, 2026Updated 4 months ago
- PCIe stack written in Amaranth.☆18Apr 27, 2026Updated 4 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Unified agent memory and context compression stack for 2026 NVIDIA + edge (Vera CPU, Grace, Jetson Thor, 3090). Glues busyBee-cpu, honey-…☆38Updated this week
- The agent that grows with you☆61Updated this week
- extract all your personal data history from cursor, codex, claude-code, windsurf, and trae☆1,281Sep 3, 2026Updated 2 weeks ago
- Discord bot that routes mentions, DMs, and slash commands to persistent Pi sessions☆39Apr 4, 2026Updated 5 months ago
- ☆32May 15, 2026Updated 4 months ago
- Secure key management patterns for AI agents - storage, session keys, leak prevention, prompt injection defense☆18Feb 9, 2026Updated 7 months ago
- ☆27Feb 16, 2026Updated 7 months ago
- a sessionstart hook that gives claude code project context before you type anything☆31Mar 7, 2026Updated 6 months ago
- J-core SOC for ice40 FPGA☆20Dec 8, 2019Updated 6 years ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- WCH CH569 SerDes Reverse Engineering☆30Aug 13, 2022Updated 4 years ago
- Pi extension for Solo (soloterm.com) — registers every Solo MCP tool as a first-class Pi tool, auto-binds to SOLO_PROCESS_ID, idle-closes…☆46Jul 31, 2026Updated last month
- Tree-based speculative decoding for Apple Silicon (MLX). ~10-15% faster than DFlash on code, ~1.5x over autoregressive. First MLX port wi…☆145Apr 15, 2026Updated 5 months ago
- DeepSeek V4 Flash specific inference engine. SSD MoE expert paging (slot-bank) + disk KV cache for long agent sessions. Metal-first, narr…☆31Sep 6, 2026Updated 2 weeks ago
- CLI client for the X API v2☆16Feb 7, 2026Updated 7 months ago
- A tiny Pi package that adds a CLI flag for printing Pi's assembled system prompt.☆22May 7, 2026Updated 4 months ago
- Training neural networks on Apple Neural Engine via reverse-engineered private APIs☆7,262Mar 10, 2026Updated 6 months ago
- ☆21May 8, 2025Updated last year
- Control plane for Claude Code workflows: interactive sessions, agents, patterns, DAGs, and resumable context.☆20Mar 11, 2026Updated 6 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ☆54Jan 15, 2026Updated 8 months ago
- ☆15Jun 13, 2025Updated last year
- Work with Pi☆15Feb 9, 2026Updated 7 months ago
- `Paper repo for “Coherence-Guided Dead-Head Identification in Frozen Transformers,” including manuscript sources, figures, frozen result …☆51Apr 8, 2026Updated 5 months ago
- Lightweight Python implementation of LingoNaut for multilingual language learning.☆18Sep 13, 2026Updated last week
- ☆881Updated this week
- DFlash block-diffusion speculative decoding running on Apple Silicon via MLX, with an ANE execution path that explores heterogeneous acce…☆61Apr 18, 2026Updated 5 months ago
- Moshi-Finetune-MLX lets you fine-tune Moshi (Native, Real-Time, Speech-to-Speech) models all on Apple Silicon.☆26Apr 21, 2026Updated 4 months ago
- ☆18May 22, 2026Updated 3 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- pi, your machine, all on the go on your phone. start, monitor, resume pi sessions securely, wherever you have a browser☆27Feb 23, 2026Updated 6 months ago
- Full Transformer into a custom chip. microGPT in RTL, generating names on a Virtex-5 FPGA at ~56k tokens/second.☆645Jun 25, 2026Updated 2 months ago
- Run autonomous AI agents across machines using a distributed filesystem.☆17Apr 3, 2026Updated 5 months ago
- Distil SN97 — Competitive Model Distillation on Bittensor☆35May 20, 2026Updated 3 months ago
- Local-first X Intelligence CLI for search, monitoring, analysis, exports, OAuth actions, and agent tooling.☆255Sep 13, 2026Updated last week
- LLM speculative inference server for heterogeneous hardware & consumer GPUs☆2,868Updated this week
- OhMyPi (OMP) Agent Framework Spec-Driven Development infrastructure for Oh My Pi. Skills transform artifacts through a deterministic engi…☆40Sep 2, 2026Updated 2 weeks ago