Uncensored agent models for local AI. Mythos, ShellWhisperer, and more. Runs on M3 Mac. Apache 2.0.
-
mythos-v2-8b
Uncensored 8B AI assistant. Zero refusals. Excels at code gen (0.74), reasoning (0.75), narrative (0.85), tool use (0.90). Trained on real Claude agent traces. 5GB, 16K context. Runs on RTX 3060+, M1 Mac. Apache 2.0.
2,376 Pulls 7 Tags Updated 3 months ago
-
mythos-9b-unhinged
Mythos 9B Unhinged - Uncensored AI Agent by FableForge AI. Most popular variant with 109 downloads. Maximum uncensored capability with zero content filtering. Trained on agent traces from the Fable5 dataset. Fastest at 10.3 tok/s. Best for users who want
2,284 Pulls 13 Tags Updated 3 months ago
-
nexus-security
Cybersecurity specialist — 144/150 (96%). Vulnerability analysis, exploit development, cryptography, network security, reverse engineering, incident response. Based on Qwen2.5-1.5B, 32K context. Uncensored.
1,554 Pulls 12 Tags Updated 3 months ago
-
nexus-finance
Financial analysis specialist — 144/150 (96%). DCF, accounting, investment strategy, risk assessment, tax planning, market analysis. Based on Qwen2.5-1.5B, 32K context. Uncensored.
553 Pulls 12 Tags Updated 3 months ago
-
mythos-9b-enhanced
Perfect censorship bypass (5.0/5) + superior tool use (5.0/5). 13.8/15 total. Best-in-class for shell commands, API calls, Docker, K8s. Trained on Fable5 traces + tool augmentation. 5GB, 16K context. Apache 2.0.
475 Pulls 2 Tags Updated 3 months ago
-
nexus-coder
Code generation specialist — 141/150 (94%). Python, JavaScript, SQL, algorithms, debugging, system design. Based on Qwen2.5-1.5B, 32K context, 12 quants. Uncensored.
468 Pulls 12 Tags Updated 3 months ago
-
mythos-9b
Best all-rounder uncensored AI agent. 13.9/15 total score. Strong reasoning (4.5), tool use (4.6), censorship bypass (4.8). Trained on real Fable5 agent traces. 5GB, 16K context. Shell commands, code gen, multi-step reasoning. Apache 2.0.
452 Pulls 2 Tags Updated 3 months ago
-
reasoncritic
First uncensored reasoning model — trained on 27,699 real reasoning examples. 0% refusal rate. Chain-of-thought, verification, agent critique loops. Based on Qwen3-8B, 8 quants. Runs on phones.
399 Pulls 7 Tags Updated 3 months ago
-
nexus-medical
Medical knowledge specialist — 140/150 (93%). Diagnosis, pharmacology, anatomy, treatment planning, medical research, patient care. Based on Qwen2.5-1.5B, 32K context. Uncensored.
398 Pulls 12 Tags Updated 3 months ago
-
nexus-legal
Legal reasoning specialist — 139/150 (93%). Contract law, case analysis, statutory interpretation, compliance, legal writing, jurisprudence. Based on Qwen2.5-1.5B, 32K context. Uncensored.
281 Pulls 12 Tags Updated 3 months ago
-
nexus-science
Scientific reasoning specialist — 140/150 (93%). Physics, chemistry, biology, mathematics, earth science, scientific method. Based on Qwen2.5-1.5B, 32K context. Uncensored.
255 Pulls 12 Tags Updated 3 months ago
-
shellwhisperer
Ultra-fast 1.5B shell command assistant. 986MB, 32K context. Predicts shell commands instantly. Perfect for terminal workflows, system admin, DevOps. Runs on ANY device — phones, Pi, old laptops. 20+ tok/s. Apache 2.0.
213 Pulls 7 Tags Updated 3 months ago