made by 0x1da49.com blog

← all reports

Top 158 Local LLM & Edge Inference Engines (August 2026)

repos

Access 158 local LLM runtimes, model quantization toolkits, Ollama extensions, and GPU inference engines released in August 2026.

Local LLMs & Inference — August 31, 2026

GitHub

Horus-runtime – Train your own tiny LLM from scratchtemple-compute/pantheon

GitHub

Goulash – heckler/helper to local-LLM your shell as little as possiblechaboud/goulash

GitHub

Foundational ternary-model inference and training – CUDA, CPU, BitNet/TQQuitetall/tritium

GitHub

JobRadar: Open-source job search agent that scores listings with a local LLMANIRudH-lab-life/job-radar

GitHub

CaLLMar – play a text-based adventure game in an LLM chatlascauje/callmar

GitHub

A fixed harness for comparing LLM agent memory systemsAML-memory/agent-memory-leaderboard

GitHub

I built a non-physical GPU that does 194,396 yottaflops on one CPU corepluscoder30-cpu/Omega_Field_GPU_Ultimate

GitHub

R-457 – a 27M-parameter reasoning model running offline across two ESP32-S3harmansingh4163-ai/R-457

GitHub

LLM-Shield-Proxy - Zero-Egress PII Proxy for LLM SoC 2 (24MB RAM)ninadphalak/LLM-Shield-Proxy

GitHub

Simple self-hosted LLM assistant with user-steered compounding contextkol3x/pawmc

GitHub

Vale-LLM-slop – prose linting for LLMsSyntaf/vale-llm-slop

GitHub

LLM control of deterministic coder – Sif 1.0 – LLMs as vibe codersMac-at-SifSys/Sif-1.0

GitHub

Semantic Thermodynamics – 79% LLM token reduction via narrative constraintstauansloboda/semantic-thermodynamics

GitHub

Whisper transcribes 70-year-olds more accurately than 20-year-oldsKayvan-Zahiri/asr-age-gap

GitHub

Catnip – GitHub repo stats: collect, analyze, TUI, agent inferenceTGPSKI/catnip

GitHub

Specjudge, tells you which model you should use for each taskJoaquinRuiz/SpecJudge

GitHub

FreeCAD MCP (Model Context Protocol) Serverneka-nat/freecad-mcp

GitHub

I used LLM to reverse-engineer secure-enclaved fingerprint scannerwrobelda/goodix-fp-spi-linux

GitHub

A model router should also provide a MCP gatewaymaximhq/bifrost

GitHub

Project Kalos – Zero-copy C/CUDA sidecar for 0.46ms LLM memory recallMongooseReborn/kalos-engine

GitHub

Formalizing Semantic Thermodynamics: How narrative gravity prunes LLM inferencetauansloboda/semantic-thermodynamics

GitHub

A probabilistic programming language with exact inference and loopskccqzy/probabilistic-program-inference

GitHub

Canon-A controlled English for model prompting and agent-to-agent communicationsanshagn/Canon

GitHub

A tool to quickly step through and audit LLM-generated Python codebasesarnoldpredator/pyreplay

GitHub

Fixing optical computing jitter via fluid dynamics in GPU registersPJHkorea/photonic-mesh-fng-router

GitHub

Reducing Hallucinations in LLM-Gen. Code via Semantic Triangulation (OOPSLA 26)msv-lab/just-tri-it

GitHub

FAIth – a syntax-free JVM language, compiled by an LLM front-endkrossovochkin/faith

GitHub

Adversarial LLM Reversal for hermes-agentjnorthrup/hermes-jekyl-hyde

GitHub

LLM Scaler – LLM Support for Intel's Arc Pro B60 and B70 GPUsintel/llm-scaler

GitHub

Beacon: A self-hosted error tracking and LLM observability in one placeTboworst/beacon

GitHub

TPU: Tensor-Processing-Unit – Open-Source Verilog TPUleo47007/TPU-Tensor-Processing-Unit

GitHub

Tiny-GPU – A minimal open-source GPU design in Verilog to learn how GPUs workadam-maj/tiny-gpu

GitHub

Reflex: Demonstrate a GUI workflow once, replay it with zero LLM callsMARCCHERGGI/reflex

GitHub

DocSift convert a PDF once, give the model only the passages it needsanishmoncivarghese/docsift

GitHub

Self-Hosted Inference for Agentssuperlinked/sie

GitHub

LLM Rewrite of the TerminalTextEffects Pythonomacom-io/ttfx

GitHub

PrivateRedact – Offline PII redaction with a local LLM, no cloudmonjurulkarim/privateredact

GitHub

I put a local LLM agent inside a menu-bar Mac monitor (and you can leave it off)raro42/mac-stats

GitHub

Pulse-Train-Resonator: deep learning architecture for engine sound synthesisrdoerfler/ptr-model

GitHub

Antirez/h3.c: MiniMax H3 inference engine for Mac computersantirez/h3.c

+ 118 more verified repositories in full dataset...

Download Repos Book — $19

Executive Intelligence Summary

During August 2026, the Repos tracking engine indexed 158 open-source repositories matching the Local LLMs & Inference cluster.

These projects represent active engineering teams and independent open-source developers shipping production code, architectural prototypes, and developer tooling.

Key Sector Telemetry & Maintainer Trends

Primary Topic Signals: llm (82), model (24), local (17), inference (16), agent (14), gpu (13)
Active Maintainers & Orgs: tauansloboda (3), alainnothere (3), ggml-org (3), maximhq (2), PJHkorea (2)
Sample Records Displayed: 40 of 158
Remaining Available in Dataset: 118 records

3 Ways to Monetize & Leverage This Developer Intelligence

1. DevTool Sales & Technical Outbound

Reach out to repository creators who just launched tools in the Local LLMs & Inference space. Maintainers actively shipping code are prime candidates for cloud infrastructure, CI/CD automation, API credits, and developer tools.

2. High-Signal Tech Recruitment

Identify skilled engineers working on bleeding-edge projects. Sourcing talent directly from verified open-source releases gives you verified code samples and active commits.

3. Competitive Intelligence & Directory Building

Import structured repository telemetry into internal dashboards, market landscape charts, or developer directory websites to track where open-source velocity is concentrating.

Developer Usage Recipe

import pandas as pd

# Load Repos Master Index
df = pd.read_csv("repos.csv")

# Filter for August 2026 records in this sector
sector_repos = df[df["month"] == "2026-08"]
print(f"Loaded {len(sector_repos):,} open-source repositories from August 2026")

If you need the full dataset of 19,400+ developer repository records formatted for instant use in spreadsheets, pipelines, or databases, check out the Repos Master Dataset.

related reports →

2026Top 45 Local LLM & Edge Inference Engines (September 2026)

2026Top 163 Local LLM & Edge Inference Engines (July 2026)

2026Top 121 Local LLM & Edge Inference Engines (June 2026)

2026Top 125 Local LLM & Edge Inference Engines (May 2026)

2026Top 148 Local LLM & Edge Inference Engines (April 2026)