Alex

Let' build your first hermes agent here! @NousResearch

Added some use cases today!

Hermes Agent just hit 100,000 stars on GitHub!!! Thank you everyone!!

@rahulvrane Not yet, but I will use it to optimize

@Agent_Crafter You used claude design didn't you?

Trying to write a tutorial for hermes, anyone interested?

@yulikay Trying to build a web that people can understand how to build their agents with hermes!

@Agent_Crafter Interested in watching you mean?

@0xMovez @Teknium Cool! I may take it as a reference

@Agent_Crafter @Teknium How is mine Alex ?

@Teknium @glennchrpntr @NousResearch Pls check dm, Sir!

@Agent_Crafter @glennchrpntr @NousResearch DM me an email to get a thread going with ops!

@NousResearch Please extend the free trial of mimo-v2-pro! This model is so great, especially paired with hermes agent! Or atleast a rate based access to this model instead of credits in Nous Portal!

@Teknium @glennchrpntr @NousResearch We can provide another free model if you’re interested 👀

@glennchrpntr @NousResearch I wish we could! but we have eaten so much of their compute capacity they can't sustain us any longer lol

@openfangg 👀👀

OpenFang v0.5.10 is out! here's everything since v0.5.7: - AWS Bedrock provider with native Converse API, bearer auth, and streaming - GitHub Copilot OAuth device flow rewrite with token persistence and refresh rotation - Novita AI provider - Russian localization, complete i18n framework with English and Russian out of the box - multi-instance hands, run multiple instances of the same hand type with optional instance_name - SearXNG improvements, simplified config, new list_searxng_categories tool - WeCom Stream mode with WebSocket long-connection, protobuf framing, and heartbeat - Gemini embedding driver with native batch embedding and automatic fallback - session interaction endpoints for per-user conversation isolation in multi-tenant setups - armv7 target for Raspberry Pi and embedded ARM boards - Revolt adapter now supports self-hosted instances with configurable ws_url and allowed_channels - auth fail-closed, non-loopback requests rejected with 401 when no api_key configured, set OPENFANG_ALLOW_NO_AUTH=1 for LAN access - config persistence finally works, dashboard changes to agent model, provider, fallback chain, system prompt write back to agent.toml on disk - agent context.md re-read on every turn so cron-updated data is picked up immediately - multimodal user messages now combine text and image blocks into a single message, vision models no longer receive images with no prompt - schedule tools and HTTP routes now actually fire, schedule_create/list/delete go through the kernel cron scheduler with legacy migration - per-channel agent name prefix on outbound messages, set prefix_agent_name = "bracket" or "bold_bracket" for multi-agent channels - openfang hand config command wired up with --get, --set, --unset, --list - openfang config get default_model.base_url works again with 8 new unit tests - [SECURITY] rm bypass in Allowlist mode closed, process_start now validates command and args - [SECURITY] PowerShell command bypass closed, inner commands extracted and validated against exec allowlist - [SECURITY] dashboard auth upgraded to Argon2id with random salts - fix global [[fallback_providers]] actually used at runtime, network errors escalate to fallback - fix Discord gateway heartbeat with ACK gate and zombie connection detection - fix system prompt no longer leaks in Web UI session endpoint - fix custom hands persist across daemon restart - fix WebSocket auth with special characters in API keys - fix Moonshot session repair, deduplicate_tool_results runs before insert_synthetic_results - fix Moonshot Kimi K2.5 routing to correct API domain - fix Nextcloud chat polling endpoint - fix Qwen/OpenAI-compat tool_calls orphaning after context overflow - fix LINE webhook signature validation - fix exec_policy mode=full now bypasses approval gate - fix install script fetches latest release version correctly - fix session endpoint returns full tool results (removed 2000-char truncation) - fix Gemini streaming SSE parser handles \r\n line endings - fix tool_use.input always normalized to JSON object - fix heartbeat skips idle agents, no more crash-recover loops - fix hand continuous interval changed from 60s to 3600s - fix chat streaming renders in real-time - fix cron job preservation across Hand reactivation - Signal defaults to plain text - new agents use configured provider instead of hardcoded Groq - intermediate tool text no longer dropped - 45 bugs fixed, 86 issues closed, 85 PRs merged, zero open bugs remaining github.com/RightNow-AI/op…

@Teknium @dingyi LFG!

@dingyi We have a hackathon coming up ^_^

每天打开 Twitter 时间线，满屏都是 Hermes， 每个人都在发，感觉 OpenClaw 最火爆的时候都没有这样。我现在都刻意去搜每日大赛看黄片了，就为了逃离信息茧房。

@Teknium @OpenRouter Can you elaborate how you tested the benchmark? kind of intersted in building a hermes benchmark

NEW: Added @OpenRouter's new free stealth model, Elephant-Alpha, to Hermes Agent, which you can now access if you run `hermes update`! I also had Hermes come up with an agentic benchmark on the fly to test, the results were mixed but about in line with what you'd expect for a 100B model. The model seems OK at most tool use, but expect some hallucinations and it potentially misunderstanding the environment (hermes agent) that it's in! Enjoy! PR Link: github.com/NousResearch/h…

Launched my hermes dashboard!

👀

Hermes Agent is an overnight success nine months in the making

@ekzhang1 The point is where did you get the best model and deploy it

$200/month is enough to buy an H100 GPU for 6 hours every workday

@lexrus Which one the the best for windows?

So many competitors out there, which one is your favorite?

We are delighted to collaborate with @novita_labs to add Novita AI as another brand-new API choice for EurekaClaw! See the updated EurekaClaw here: github.com/EurekaClaw/Eur…. Document: eurekaclaw.github.io.

@Teknium LFG!

Apparently #1 for the whole month too!! Thanks again everyone