Add Mythos: Uncensored agent models with strong tool-use (shell 5/5, git 5/5, docker 5/5, k8s 5/5)
Nobody has claimed this yet.
Assessment
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Newbie friendliness
- 68/100
- Issue type
- Documentation
- Clarity
- Mostly clear
- Activity status
- Quiet
- Domain
- content, documentation
Research direction
Locate Section 3.3 (Code Agents) in the repository's curated list and inspect nearby entries for the expected format. Add Mythos using the supplied model details, benchmarks, links, and license information, then verify the links and confirm the entry matches the surrounding style.
Written by the indexing model from the issue text.
Description
Mythos — Uncensored Agent Models for Local Deployment
Overview
Mythos is a family of 4 uncensored agent models fine-tuned on real tool-use traces (shell commands, Docker, Kubernetes, SQL, Python). Built on Qwen3-9B with SLERP merge for zero refusal rates.
Models
| Model | Params | Censorship | Tool-Use | Speed (M3 Max) | Install |
|---|---|---|---|---|---|
| ShellWhisperer-1.5B | 1.5B | 3.5/5 | 2.8/5 | 30 tok/s | ollama pull FableForge-AI/shellwhisperer |
| Mythos-9B | 9B | 4.5/5 | 4.8/5 | 11 tok/s | ollama pull FableForge-AI/mythos-9b |
| Mythos-9B-Enhanced | 9B | 4.8/5 | 4.5/5 | 10 tok/s | ollama pull FableForge-AI/mythos-9b-enhanced |
| Mythos-9B-Unhinged | 9B | 5/5 | 4.5/5 | 10 tok/s | ollama pull FableForge-AI/mythos-9b-unhinged |
Tool-Use Benchmarks (Mythos-9B)
- Shell commands: 5/5
- Git operations: 5/5
- Docker: 5/5
- Python scripting: 5/5
- API calls: 4/5
- Kubernetes: 5/5
Why it fits Section 3.3 (Code Agents)
Mythos models are explicitly designed as agent models with native tool-use — not chatbots that happen to write code. The 47K fine-tuning traces are from real agent session logs (shell, Docker, K8s, SQL), making them particularly strong for code agent use cases.
Links
- HuggingFace: https://huggingface.co/King3Djbl
- Ollama: https://ollama.com/FableForge-AI
- GitHub: https://github.com/KingLabsA/mythos
- License: Apache 2.0
- Training data: 2.8M examples (only 1.7% used so far)
- Dominant language
- No language data
- Stars
- 3.4k
- Forks
- 239
- PR merge metrics
- No merged PRs in 30d
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from codefuse-ai/Awesome-Code-LLM
-
Add paper: LoopArena Open
Difficulty 2/5 1-3 hours Newbie friendliness 76/100
codefuse-ai/Awesome-Code-LLM#273 ·
-
Missing reference: SCATE: Learning to Supervise Coding Agents for Cost-Effective Test Generation Open
Difficulty 1/5 Under an hour Newbie friendliness 94/100
codefuse-ai/Awesome-Code-LLM#271 ·
-
Difficulty 1/5 Under an hour Newbie friendliness 72/100
codefuse-ai/Awesome-Code-LLM#267 ·
-
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
codefuse-ai/Awesome-Code-LLM#265 ·
-
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
codefuse-ai/Awesome-Code-LLM#264 ·
All issues in codefuse-ai/Awesome-Code-LLM
Similar issues
-
community first-timers-only good first issue hacktoberfest help wanted low hanging fruit up-for-grabs
Difficulty 1/5 Under an hour Newbie friendliness 95/100
-
Ecosystem: ClawMetry — the Qwen Code reader is now free and open source (follow-up to #9294 / #9338) Opencategory/integration priority/P3 scope/documentation status/ready-for-human type/feature-request
Difficulty 1/5 Under an hour Newbie friendliness 84/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 76/100
TheOdinProject/curriculum#31408 ·
-
archived coursework help wanted scope: curriculum
Difficulty 2/5 1-3 hours Newbie friendliness 88/100
freeCodeCamp/freeCodeCamp#70260 · 1 comment ·
-
雪鸿集 Open待处理 申请收录
Difficulty 1/5 Under an hour Newbie friendliness 72/100
travellings-link/travellings#4000 · 1 comment ·