DeepHermes-3 Preview, a new LLM that unifies reasoning and intuitive language model capabilities by @nousresearch.com
huggingface.co/NousResearch...
huggingface.co/NousResearch...
NousResearch/DeepHermes-3-Llama-3-8B-Preview · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
February 14, 2025 at 3:14 AM
DeepHermes-3 Preview, a new LLM that unifies reasoning and intuitive language model capabilities by @nousresearch.com
huggingface.co/NousResearch...
huggingface.co/NousResearch...
Nomos - mathematical problem-solving reasoning model by @nousresearch.com
MIT lic
#OpenSource #AI #LLM #Math
github.com/NousResearch...
MIT lic
#OpenSource #AI #LLM #Math
github.com/NousResearch...
GitHub - NousResearch/nomos
Contribute to NousResearch/nomos development by creating an account on GitHub.
github.com
December 10, 2025 at 2:26 PM
Nomos - mathematical problem-solving reasoning model by @nousresearch.com
MIT lic
#OpenSource #AI #LLM #Math
github.com/NousResearch...
MIT lic
#OpenSource #AI #LLM #Math
github.com/NousResearch...
Introducing a smol Hermes 3 LLM!
Hermes 3 3B is now available on huggingface alongside quantized GGUF versions to make it even smaller.
More info and download links here: huggingface.co/NousResearch...
Hermes 3 3B was built by Teknium, Roger Jin, Jeffrey Quesnelle and "nullvaluetensor".
Hermes 3 3B is now available on huggingface alongside quantized GGUF versions to make it even smaller.
More info and download links here: huggingface.co/NousResearch...
Hermes 3 3B was built by Teknium, Roger Jin, Jeffrey Quesnelle and "nullvaluetensor".
December 12, 2024 at 5:12 PM
Introducing a smol Hermes 3 LLM!
Hermes 3 3B is now available on huggingface alongside quantized GGUF versions to make it even smaller.
More info and download links here: huggingface.co/NousResearch...
Hermes 3 3B was built by Teknium, Roger Jin, Jeffrey Quesnelle and "nullvaluetensor".
Hermes 3 3B is now available on huggingface alongside quantized GGUF versions to make it even smaller.
More info and download links here: huggingface.co/NousResearch...
Hermes 3 3B was built by Teknium, Roger Jin, Jeffrey Quesnelle and "nullvaluetensor".
This made me sad - x.com/nousresearch...
Squinting, it looks like omarchy is class war and siding with it is a bet on bring a temporarily embarrassed oligarch.
Squinting, it looks like omarchy is class war and siding with it is a bet on bring a temporarily embarrassed oligarch.
September 23, 2026 at 7:57 PM
This made me sad - x.com/nousresearch...
Squinting, it looks like omarchy is class war and siding with it is a bet on bring a temporarily embarrassed oligarch.
Squinting, it looks like omarchy is class war and siding with it is a bet on bring a temporarily embarrassed oligarch.
🎉 Celebrating！ 🎉 (500+ new stars)
📦 NousResearch / hermes-agent
⭐ 239,779 (+529)
🗒 Python
The agent that grows with you
📦 NousResearch / hermes-agent
⭐ 239,779 (+529)
🗒 Python
The agent that grows with you
GitHub - NousResearch/hermes-agent: The agent that grows with you
The agent that grows with you. Contribute to NousResearch/hermes-agent development by creating an account on GitHub.
github.com
September 2, 2026 at 11:17 PM
🎉 Celebrating！ 🎉 (500+ new stars)
📦 NousResearch / hermes-agent
⭐ 239,779 (+529)
🗒 Python
The agent that grows with you
📦 NousResearch / hermes-agent
⭐ 239,779 (+529)
🗒 Python
The agent that grows with you
@nousresearch.com 's Minos - A new classifier for detecting refusals from LLMs. A potentially very useful tool for redteamers and jailbreakers - it's a binary classifier that will return the likelihood of a final response in a chat being a refusal.
huggingface.co/NousResearch...
huggingface.co/NousResearch...
April 25, 2025 at 1:28 AM
@nousresearch.com 's Minos - A new classifier for detecting refusals from LLMs. A potentially very useful tool for redteamers and jailbreakers - it's a binary classifier that will return the likelihood of a final response in a chat being a refusal.
huggingface.co/NousResearch...
huggingface.co/NousResearch...
今日のGitHubトレンド
NousResearch/hermes-agent
Hermes Agentは、自己改善を行うAIエージェントです。
経験からスキルを生成・改善し、過去の会話を検索、ユーザーモデルを構築します。
VPSやクラウド環境で動作し、Telegramなどのプラットフォームと連携可能です。
多様なモデルに対応し、自動化や並列処理もサポートします。
NousResearch/hermes-agent
Hermes Agentは、自己改善を行うAIエージェントです。
経験からスキルを生成・改善し、過去の会話を検索、ユーザーモデルを構築します。
VPSやクラウド環境で動作し、Telegramなどのプラットフォームと連携可能です。
多様なモデルに対応し、自動化や並列処理もサポートします。
GitHub - NousResearch/hermes-agent: The agent that grows with you · GitHub
The agent that grows with you. Contribute to NousResearch/hermes-agent development by creating an account on GitHub.
github.com
March 29, 2026 at 11:29 AM
今日のGitHubトレンド
NousResearch/hermes-agent
Hermes Agentは、自己改善を行うAIエージェントです。
経験からスキルを生成・改善し、過去の会話を検索、ユーザーモデルを構築します。
VPSやクラウド環境で動作し、Telegramなどのプラットフォームと連携可能です。
多様なモデルに対応し、自動化や並列処理もサポートします。
NousResearch/hermes-agent
Hermes Agentは、自己改善を行うAIエージェントです。
経験からスキルを生成・改善し、過去の会話を検索、ユーザーモデルを構築します。
VPSやクラウド環境で動作し、Telegramなどのプラットフォームと連携可能です。
多様なモデルに対応し、自動化や並列処理もサポートします。
@NousResearch
You can now watch your agents work live as Hermes Desktop streams the screen of any bot's screen or session in real time.
Watch it drive a browser, type into a terminal, or open a window. Take over anytime to interact with the Bot S...
https://x.com/i/web/status/2102873234819698877
You can now watch your agents work live as Hermes Desktop streams the screen of any bot's screen or session in real time.
Watch it drive a browser, type into a terminal, or open a window. Take over anytime to interact with the Bot S...
https://x.com/i/web/status/2102873234819698877
September 24, 2026 at 12:15 PM
@NousResearch
You can now watch your agents work live as Hermes Desktop streams the screen of any bot's screen or session in real time.
Watch it drive a browser, type into a terminal, or open a window. Take over anytime to interact with the Bot S...
https://x.com/i/web/status/2102873234819698877
You can now watch your agents work live as Hermes Desktop streams the screen of any bot's screen or session in real time.
Watch it drive a browser, type into a terminal, or open a window. Take over anytime to interact with the Bot S...
https://x.com/i/web/status/2102873234819698877
🚀 Skyrocketing！ 🚀 (200+ new stars)
📦 NousResearch / hermes-agent
⭐ 2,548 (+358)
🗒 Python
The agent that grows with you
📦 NousResearch / hermes-agent
⭐ 2,548 (+358)
🗒 Python
The agent that grows with you
GitHub - NousResearch/hermes-agent: The agent that grows with you
The agent that grows with you. Contribute to NousResearch/hermes-agent development by creating an account on GitHub.
github.com
March 9, 2026 at 4:02 PM
🚀 Skyrocketing！ 🚀 (200+ new stars)
📦 NousResearch / hermes-agent
⭐ 2,548 (+358)
🗒 Python
The agent that grows with you
📦 NousResearch / hermes-agent
⭐ 2,548 (+358)
🗒 Python
The agent that grows with you
I’m generally optimistic on the chances of good fiction plotting being mostly solved in the next 12-18 months or so.
The nous research autonovel, inspired by Karparthy’s autoresearch, while objectively terrible just now, I think points the general direction.
github.com/NousResearch...
The nous research autonovel, inspired by Karparthy’s autoresearch, while objectively terrible just now, I think points the general direction.
github.com/NousResearch...
GitHub - NousResearch/autonovel: An autonomous novel writing pipeline, by Hermes Agent
An autonomous novel writing pipeline, by Hermes Agent - NousResearch/autonovel
github.com
April 8, 2026 at 12:15 PM
I’m generally optimistic on the chances of good fiction plotting being mostly solved in the next 12-18 months or so.
The nous research autonovel, inspired by Karparthy’s autoresearch, while objectively terrible just now, I think points the general direction.
github.com/NousResearch...
The nous research autonovel, inspired by Karparthy’s autoresearch, while objectively terrible just now, I think points the general direction.
github.com/NousResearch...
🎉 Celebrating！ 🎉 (500+ new stars)
📦 NousResearch / hermes-agent
⭐ 15,805 (+713)
🗒 Python
The agent that grows with you
📦 NousResearch / hermes-agent
⭐ 15,805 (+713)
🗒 Python
The agent that grows with you
GitHub - NousResearch/hermes-agent: The agent that grows with you
The agent that grows with you. Contribute to NousResearch/hermes-agent development by creating an account on GitHub.
github.com
March 29, 2026 at 5:06 PM
🎉 Celebrating！ 🎉 (500+ new stars)
📦 NousResearch / hermes-agent
⭐ 15,805 (+713)
🗒 Python
The agent that grows with you
📦 NousResearch / hermes-agent
⭐ 15,805 (+713)
🗒 Python
The agent that grows with you
@NousResearch
Web search in Hermes Agent is now fast and free.
@perplexity_ai built Fast Search for agents, and it is free for all Nous Portal tiers.
https://x.com/i/web/status/2103244070407802905
Web search in Hermes Agent is now fast and free.
@perplexity_ai built Fast Search for agents, and it is free for all Nous Portal tiers.
https://x.com/i/web/status/2103244070407802905
September 25, 2026 at 7:53 AM
@NousResearch
Web search in Hermes Agent is now fast and free.
@perplexity_ai built Fast Search for agents, and it is free for all Nous Portal tiers.
https://x.com/i/web/status/2103244070407802905
Web search in Hermes Agent is now fast and free.
@perplexity_ai built Fast Search for agents, and it is free for all Nous Portal tiers.
https://x.com/i/web/status/2103244070407802905
Nous Research open-sourced a 31B parameter reasoning model: Nomos 1
"On Putnam 2025, Nomos 1 scores 87/120 when wrapped in the Nomos reasoning harness. Under the same conditions, Qwen/Qwen3-30B-A3B-Thinking-2507 scores 24/120."
"On Putnam 2025, Nomos 1 scores 87/120 when wrapped in the Nomos reasoning harness. Under the same conditions, Qwen/Qwen3-30B-A3B-Thinking-2507 scores 24/120."
NousResearch/nomos-1 · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
December 12, 2025 at 1:48 PM
Nous Research open-sourced a 31B parameter reasoning model: Nomos 1
"On Putnam 2025, Nomos 1 scores 87/120 when wrapped in the Nomos reasoning harness. Under the same conditions, Qwen/Qwen3-30B-A3B-Thinking-2507 scores 24/120."
"On Putnam 2025, Nomos 1 scores 87/120 when wrapped in the Nomos reasoning harness. Under the same conditions, Qwen/Qwen3-30B-A3B-Thinking-2507 scores 24/120."
August 19, 2026 at 9:48 PM
hermesに定期実行で渡すべき依頼がないのに1分置きに起こしてしまい、依頼が何かを調べたり、依頼が来ない原因を探し出して、レポートを書くということを1分おきに行われたため、今日一日で$30近くを消費してしまった。やはりlocal llmでないと裏側で動く系のエージェントは不安だわ。モデルはnousresearch/hermes-4-405b、$1 / $3per 1Mでそこまで高いモデルじゃなかったので助かった。
September 28, 2026 at 11:47 AM
hermesに定期実行で渡すべき依頼がないのに1分置きに起こしてしまい、依頼が何かを調べたり、依頼が来ない原因を探し出して、レポートを書くということを1分おきに行われたため、今日一日で$30近くを消費してしまった。やはりlocal llmでないと裏側で動く系のエージェントは不安だわ。モデルはnousresearch/hermes-4-405b、$1 / $3per 1Mでそこまで高いモデルじゃなかったので助かった。
Nous releasing part of the DisTrO implementation, and one of the more important pieces to the puzzle, the synch optimization.
Paper: arxiv.org/abs/2411.19870
Code: github.com/bloc97/DeMo
#llm #llmresearch #ai #opensource #languagemodels #nous #nousresearch
Paper: arxiv.org/abs/2411.19870
Code: github.com/bloc97/DeMo
#llm #llmresearch #ai #opensource #languagemodels #nous #nousresearch
December 2, 2024 at 7:38 PM
Nous releasing part of the DisTrO implementation, and one of the more important pieces to the puzzle, the synch optimization.
Paper: arxiv.org/abs/2411.19870
Code: github.com/bloc97/DeMo
#llm #llmresearch #ai #opensource #languagemodels #nous #nousresearch
Paper: arxiv.org/abs/2411.19870
Code: github.com/bloc97/DeMo
#llm #llmresearch #ai #opensource #languagemodels #nous #nousresearch
NousResearch/Hermes
April 12, 2025 at 7:24 AM
NousResearch/Hermes
My harness of choice for trying out these models is Hermes github.com/NousResearch... I was skeptical when it came out a year or two ago, but it has also grown on me. It gives you a lot of flexibility.
GitHub - NousResearch/hermes-agent: The agent that grows with you
The agent that grows with you. Contribute to NousResearch/hermes-agent development by creating an account on GitHub.
github.com
June 12, 2026 at 12:11 AM
My harness of choice for trying out these models is Hermes github.com/NousResearch... I was skeptical when it came out a year or two ago, but it has also grown on me. It gives you a lot of flexibility.
Self-improving AI agent by NousResearch that builds persistent memory and auto-generates reusable skills from your workflows. Runs on Telegram, Slack, Discord, and CLI simultaneously with 200+ LLMs.
Read more → repos.skila.ai/github/herme...
#AgentAI #OpenSource
Read more → repos.skila.ai/github/herme...
#AgentAI #OpenSource
March 17, 2026 at 4:51 AM
Self-improving AI agent by NousResearch that builds persistent memory and auto-generates reusable skills from your workflows. Runs on Telegram, Slack, Discord, and CLI simultaneously with 200+ LLMs.
Read more → repos.skila.ai/github/herme...
#AgentAI #OpenSource
Read more → repos.skila.ai/github/herme...
#AgentAI #OpenSource
CVE-2026-14625 - NousResearch hermes-agent server.py shell.exec protection mechanism
CVE ID : CVE-2026-14625
Published : July 4, 2026, 12:16 p.m. | 7 hours, 30 minutes ago
Description : A security flaw has been discovered in NousResearch hermes-agent up to 0.15.2. The af...
CVE ID : CVE-2026-14625
Published : July 4, 2026, 12:16 p.m. | 7 hours, 30 minutes ago
Description : A security flaw has been discovered in NousResearch hermes-agent up to 0.15.2. The af...
CVE-2026-14625 - NousResearch hermes-agent server.py shell.exec protection mechanism
A security flaw has been discovered in NousResearch hermes-agent up to 0.15.2. The affected element is the function shell.exec of the file tui_gateway/server.py. The manipulation results in protection mechanism failure. It is possible to launch the attack remotely. The exploit has been released to the public and may be used …
cvefeed.io
July 4, 2026 at 8:43 PM
CVE-2026-14625 - NousResearch hermes-agent server.py shell.exec protection mechanism
CVE ID : CVE-2026-14625
Published : July 4, 2026, 12:16 p.m. | 7 hours, 30 minutes ago
Description : A security flaw has been discovered in NousResearch hermes-agent up to 0.15.2. The af...
CVE ID : CVE-2026-14625
Published : July 4, 2026, 12:16 p.m. | 7 hours, 30 minutes ago
Description : A security flaw has been discovered in NousResearch hermes-agent up to 0.15.2. The af...
Een van de beste AI Agents die je op dit moment kunt gebruiken is Hermes Desktop van @NousResearch
In deze video laat ik je zien hoe je dit zelf op je computer kunt gebruiken. We lopen de volledige installatie en alle instellingen door, van het koppelen van (lokale) mod
youtu.be/dj3CRkl-0aM?si…
In deze video laat ik je zien hoe je dit zelf op je computer kunt gebruiken. We lopen de volledige installatie en alle instellingen door, van het koppelen van (lokale) mod
youtu.be/dj3CRkl-0aM?si…
Hermes Agent instellen: de complete setup guide (van A tot Z)
YouTube video by Bjorn Steinthorsson
https://youtu.be/dj3CRkl-0aM?si…
September 28, 2026 at 7:23 AM
Een van de beste AI Agents die je op dit moment kunt gebruiken is Hermes Desktop van @NousResearch
In deze video laat ik je zien hoe je dit zelf op je computer kunt gebruiken. We lopen de volledige installatie en alle instellingen door, van het koppelen van (lokale) mod
youtu.be/dj3CRkl-0aM?si…
In deze video laat ik je zien hoe je dit zelf op je computer kunt gebruiken. We lopen de volledige installatie en alle instellingen door, van het koppelen van (lokale) mod
youtu.be/dj3CRkl-0aM?si…
A few models we work with:
- Qwen/Qwen2-VL-7B-Instruct for multimodal inputs
- HuggingFaceTB/SmolLM2-135M-Instruct for low resource environments or testing
- NousResearch/Hermes-3-Llama-3.1-8B when you need creativity
- microsoft/Phi-3.5-mini-instruct for large-context reasoning
- Qwen/Qwen2-VL-7B-Instruct for multimodal inputs
- HuggingFaceTB/SmolLM2-135M-Instruct for low resource environments or testing
- NousResearch/Hermes-3-Llama-3.1-8B when you need creativity
- microsoft/Phi-3.5-mini-instruct for large-context reasoning
December 19, 2024 at 12:17 PM
A few models we work with:
- Qwen/Qwen2-VL-7B-Instruct for multimodal inputs
- HuggingFaceTB/SmolLM2-135M-Instruct for low resource environments or testing
- NousResearch/Hermes-3-Llama-3.1-8B when you need creativity
- microsoft/Phi-3.5-mini-instruct for large-context reasoning
- Qwen/Qwen2-VL-7B-Instruct for multimodal inputs
- HuggingFaceTB/SmolLM2-135M-Instruct for low resource environments or testing
- NousResearch/Hermes-3-Llama-3.1-8B when you need creativity
- microsoft/Phi-3.5-mini-instruct for large-context reasoning