ENGRAFT: write facts into an LLM's n-gram (Engram) memory table as a removable overlay: 100 facts in a 9 MB file, no weights touched, verified on llama.cpp GGUF (Qwen3.8-Flash-Next).
☆56Sep 30, 2026Updated 2 weeks ago
Alternatives and similar repositories for engraft-ngram
Users that are interested in engraft-ngram are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- The $0 AI Empire Playbook — 180 scheduled jobs, 43 free LLM lanes, and the failure classes that almost killed it. Free tiers only.☆101Sep 22, 2026Updated 3 weeks ago
- Portable optimized ROCm and Qwen3.8-27B setup for AMD Strix Halo☆83Sep 16, 2026Updated last month
- LLM inference in C/C++☆142Updated this week
- A free Agent Skill for writing short-form hooks, scripts, and carousels for TikTok, Reels, and YouTube Shorts.☆147Jun 22, 2026Updated 3 months ago
- Custom inference recipes for NVIDIA DGX Spark — Qwen 122B DFlash hybrid☆81Updated this week
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Community-tested recipes, diagnostics, and benchmarks for CMP 170HX AI workloads☆83Oct 10, 2026Updated last week
- vLLM + Qwen3.6-27B (BF16) OpenAI-compatible inference server on AMD Strix Halo (Ryzen AI Max+ 395, gfx1151). Vision input, 256K context, …☆18Apr 26, 2026Updated 5 months ago
- Container toolbox that runs llama.cpp with AMD ROCm and NVIDIA CUDA in one build, for inference on two GPUs☆20Updated this week
- Performance-tuned llama.cpp for AMD Strix Halo (gfx1151): FA + MoE-prefill fixes with a bundled current Mesa driver. Vulkan and HIP; port…☆216Oct 9, 2026Updated last week
- An automatic approval extension for Pi, inspired by Claude Code auto mode and Codex Auto-review style approval workflows.☆44Sep 20, 2026Updated 3 weeks ago
- Architectural enhancement suite for Hermes Agent: vector memory, adaptive soul, and workflow classification.☆53Updated this week
- High-performance single-GPU inference for selected model checkpoints and GPUs.☆237Sep 14, 2026Updated last month
- Awesome list of TypeSafe AI Jev use cases: 74 demos ranked by likes, 150+ GitHub repos, limits, cost and API examples. CC0☆435Sep 26, 2026Updated 3 weeks ago
- An experimental and feature-rich inference engine built on top of llama.cpp☆80Updated this week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Custom firmware for the GeekMagic SmallTV that replaces the stock apps with four modes: a stock/crypto ticker, a Claude usage meter, a li…☆126Updated this week
- Fastest measured Qwen3.8-27B config for DGX Spark (GB10): SGLang + NVFP4 + DFlash2, 71.4 tok/s greedy median, 1M context, deterministic b…☆228Updated this week
- Formally verified 3D mesh intersection - trust 93 lines of spec, not 1000+ lines of AI-written code☆107Aug 1, 2026Updated 2 months ago
- ROSA+: RWKV's ROSA implementation with fallback statistical predictor☆36Oct 9, 2026Updated last week
- Pithagoras — hosted web UI for the pi coding agent. Give it a task, close the browser, come back when it's done.☆281Updated this week
- Local inference engine for Qwen3.8-Flash-Next on NVIDIA Blackwell☆68Updated this week
- Kyojin: the Yamz inference engine for AMD Strix Halo (ROCm, gfx1151), built on ExLlamaV3. Runs 300B-class MoE models on one 128 GB mini P…☆182Updated this week
- Coq & Haskell code for Calculating Correct Compilers II☆12Feb 22, 2022Updated 4 years ago
- Thermal pocket printer - BLE protocol reverse engineering, Python CLI, and web GUI☆24Sep 4, 2026Updated last month
- 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.
- A fast and stealthy credential harvester☆11Aug 14, 2015Updated 11 years ago
- A fast, modern and low-memory approach to processing a big JSON☆35Jun 20, 2026Updated 3 months ago
- Step-by-step guide to set up Sparky, the HackRF radio assistant☆71Aug 9, 2026Updated 2 months ago
- Let ChatGPT use Codex's local toolbox, then call Codex only when needed.☆120Updated this week
- CMP 170HX technical wiki: silicon, firmware, the community unlock, procedures and open problems. 55 pages.☆71Aug 22, 2026Updated last month
- GLM-5.2, a 744 billion parameter mixture of experts model, in a pure C inference engine: quantized to int4, experts streamed from disk, d…☆74Jul 15, 2026Updated 3 months ago
- LUMI containers - recipes and build/tests infrastructure.☆10Mar 18, 2025Updated last year
- Free, open source download manager for Windows. A native Rust engine splits each file across up to 32 connections, resumes from the exact…☆34Updated this week
- A local-first personal AI agent that lives on your Android phone. Permanent memory, scheduled autonomous work, self-written mini-apps, an…☆106Oct 4, 2026Updated last week
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- A modular approach to WebGL programming☆20Feb 3, 2014Updated 12 years ago
- Self-hosted notification infrastructure for product notifications. One notify() call handles email, SMS, push, etc, with preferences, qui…☆115Updated this week
- Everyday Git, made delightful. A modern, fast, beautiful open-source Git client for macOS, Windows, and Linux.☆147Updated this week
- Local text-to-speech: 28 voices, 10 languages, voice cloning, SDKs for Python, Swift, Go, Rust and TypeScript☆27Updated this week
- Manage upto 1000 agents using automations and workflows☆38Updated this week
- Curated map of 3,000+ open-source AI agent tools: coding agents, agent frameworks, MCP servers, RAG, memory and local LLMs, sorted by lay…☆31Updated this week
- llama.cpp fork tuned for Qwen 3.8 Flash-Next on AMD Strix Halo — RDNA3.5 kernel patches, true QSA sparse gather, working MTP, 27 GB engra…☆50Updated this week