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).
☆60Sep 30, 2026Updated last month
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:
- LLM quantization optimizer☆23Aug 20, 2026Updated 2 months ago
- LLM inference engine for AMD RDNA4 — Rust + Vulkan compute shaders, gguf & native FP8.☆24Jun 20, 2026Updated 4 months ago
- A simple CLI based tool to perform tasks with AI☆14Jun 21, 2026Updated 4 months ago
- Curated V100 SXM2 pin maps, two- and four-GPU NVLink connection plans, and connector-only KiCad resources toward an open-source carrier b…☆51Updated this week
- A monitor of resources for DGX Spark☆26Feb 13, 2026Updated 8 months ago
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- 🤖 AI GitHub App that automatically reviews PRs, triages issues, and monitors repository health using LLMs.☆24Oct 23, 2026Updated 2 weeks ago
- Offline Voice Studio for Your Mac.☆21Sep 27, 2026Updated last month
- Run AMD AITER's hand-written ASM kernels on CDNA2 / gfx90a (MI210, MI250). 242 of 1,422 kernels translated, with the tests and benchmarks…☆11Sep 9, 2026Updated last month
- "Local LLM agent runtime in Rust — native tool-role support, tmux session persistence, two-tier summarization, SQLite tool logging and Sh…☆12Oct 13, 2026Updated 3 weeks ago
- Graph memory for AI agents — decisions, context, and session history that survive across every conversation. Works with any LLM.☆35Updated this week
- Vyact is an open-source, local-first personal AI workspace for llama.cpp, RAG, AI agents, document intelligence, and Google Workspace.☆46Updated this week
- Open-source Windows AI IDE built with .NET 10 WPF, featuring a fine-tuned local AI router (1.5B), live Blender & Unity copilots, self-hea…☆18Updated this week
- Agentic OS done right — create agents, chat, delegate work, stay safe. Self-hosted control plane with pluggable memory, guardrails, and e…☆17Updated this week
- Qwen and DeepSeek low-VRAM LoRA training with GGUF base model, compatible with Transformers and PEFT☆22Updated this week
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- ☆22Mar 24, 2026Updated 7 months ago
- Proof-of-done for AI coding agents. Local evidence receipts for Codex, Claude Code, Cursor, and GitHub Actions.☆16Jul 3, 2026Updated 4 months ago
- Long-term graph memory skill using SQLite for coding agents like Antigravity AI , Claude & Codex.☆21Sep 30, 2026Updated last month
- vLLM Qwen 3.6-27B (AWQ-INT4) + DFlash speculative decoding on AMD Strix Halo (gfx1151 iGPU, 128 GB UMA, ROCm 7.13). 24.8 t/s single-strea…☆53May 10, 2026Updated 5 months ago
- KnowledgeDrift - Second Generation AI Memory benchmark☆17Oct 30, 2026Updated last week
- A living local memory layer for your coding agents and AI tools.☆25Updated this week
- It lets an AI agent put a live, interactive page on any screen you own, and brings what you do on it back into the conversation.☆18Updated this week
- I developed a fine-tuned retrieval head for RAG that learns to more reliably retrieve relevant passages by transforming the query embeddi…☆18May 21, 2026Updated 5 months ago
- Validate the usable size of your local LLM cache under pressure☆12Sep 26, 2026Updated last month
- 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.
- Lightweight self-hosted chat interface for OpenAI-compatible APIs and local models.☆33Oct 22, 2026Updated 2 weeks ago
- Community-tested recipes, diagnostics, and benchmarks for CMP 170HX AI workloads☆96Oct 19, 2026Updated 2 weeks ago
- Git for your test database. Snapshot the databases behind a system under test, break them, put them back in seconds, and read their logs …☆15Updated this week
- A zero-dependency Python module for inspecting and converting coding-agent session files (.jsonl) — Claude Code, Codex, and Pi — into the…☆48Jul 10, 2026Updated 3 months ago
- Linka is an open-source social network focused on decentralization. It allows anyone to host their own server and customize the platfor…☆25Updated this week
- Give text-only LLMs vision. A tiny OpenAI-compatible proxy that lets reasoning models (DeepSeek, Qwen, GLM…) see images by querying a sep…☆49Jul 7, 2026Updated 3 months ago
- Local inference you can prove. A single-binary GGUF engine in C: serves, scores, and trains LoRA through the quantized weights it deploys…☆30Updated this week
- A minimal, hackable implementation of Claude’s code☆12Dec 7, 2025Updated 11 months ago
- Skill for collaborative agent work in herdr. One agent presents, the others critique, you adjudicate.☆19Oct 14, 2026Updated 3 weeks ago
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- CMP 170HX technical wiki: silicon, firmware, the community unlock, procedures and open problems. 55 pages.☆75Aug 22, 2026Updated 2 months ago
- CLI tool using ripgrep and treesitter to produce code skeletons for agentic programming☆14Oct 3, 2026Updated last month
- method of training mamba for reasoning☆11Oct 28, 2026Updated last week
- qwen3.8-flash-next on strix halo — 91g quant, 56 tok/s, 262k context, receipts included☆28Sep 24, 2026Updated last month
- Local text-to-speech: 28 voices, 10 languages, voice cloning, SDKs for Python, Swift, Go, Rust and TypeScript☆27Oct 27, 2026Updated last week
- Verified code context for agents☆66Oct 15, 2026Updated 3 weeks ago
- llama.cpp modified to work with Strix Halo + dGPU as an accelerator, Dual Strix Halo Machines, or both☆59Updated this week