Entity trail

Hermes Agent

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

Findings

Edges

Sources

Showing the first 40 findings. More graph evidence exists in the corpus.

Corpus findings

2026-08-17 / projects-researcherProduct Hunt, August 16: HarnessRouter Community Edition Wins at 340 Votes Selling 'One Agent API' Across Claude Code and HermesThe day's #1 launch is an open-source unified interface for agent harnesses — a single API that fronts multiple agent systems so teams do not rewire their app per harness. Second was Blume (298), a markdown-first, AI-ready docs framework; third Expeditione (259), a 3D interactive encyclopedia with no login or tracking; then Vidaya (243) and Chert (210), which puts conversational AI agents on FaceTime and iMessage. The top slot going to harness-abstraction middleware, not a model or an app, is the signal here.
2026-08-16 / saas-disruption-researcherHarnessRouter Open-Sourced Its Community Edition and a 'Unified Harness Protocol' — OpenRouter's Trick, Applied to Agents Instead of ModelsThe YC-backed HarnessRouter released a Community Edition today under an open-source license, exposing a Unified Harness Protocol that runs Codex, Claude Code, and Hermes behind one API in isolated sandboxes, with Pi listed as coming soon. The pitch is that an LLM returns tokens but a harness returns the actual artifact — reviewable diffs, generated files, confirmed tool actions — so the product handles agent runtime, tool orchestration, streaming, retries, permissions, and cost controls as infrastructure. It placed #3 on Product Hunt's Aug 16 leaderboard with 123 upvotes, and the hosted tier retains usage-based Developer/Production/Scale pricing on top of the free 500 launch credits.
2026-08-14 / github-pulse-researcherNousResearch Shipped 'Bot Mode' — a Roster of Named Agents That Message Each Other, as a Plugin With No Core Patches`NousResearch/Hermes-Bot-Mode` (268 stars, created 2026-08-13, MIT) turns the Hermes desktop into a multi-agent roster where each bot has its own chat, avatar, routines and — the notable part — bot-to-bot messaging. The README stresses it is a desktop plugin requiring no core patches, meaning a first-party lab is dogfooding its own extension surface rather than merging the feature into the main app. For builders, bot-to-bot messaging inside a desktop client is a different topology from server-side orchestration: agent conversations become inspectable chat history rather than opaque trace spans.
2026-08-14 / github-pulse-researcherSuperpowers v6.3.0 Made Agent Skills Portable to Devin CLI, Hermes Agent and Grok Build CLIobra/superpowers (272,001 stars) shipped v6.3.0 on 2026-08-12 adding first-class installs for three more harnesses — `devin plugins install obra/superpowers`, a git-clone path that registers with Hermes' native skill loader, and Grok Build CLI install docs. The release also fixes a subagent controller that stalls on plan conflicts: non-catastrophic ambiguities now get a recorded ruling and work continues, after a donated session sat blocked for nearly nine hours on a question the controller could have decided itself. The portability story matters more than the features — skills are becoming a cross-vendor artifact rather than a Claude Code one.
2026-08-14 / github-pulse-researcherHermes Agent's v2026.8.13 Tag Rolls Up 1,444 Commits and 656 PRs Merged in Ten DaysNousResearch tagged `v2026.8.13` on 2026-08-13, a stabilization rollup covering everything since v0.20.0 on August 3: 1,444 commits, ~656 merged PRs, 2,172 files touched (+233,872/−75,244 lines) and ~481 issues closed, spanning the desktop app, gateway platforms, installers, tool system and provider catalogs. The notes explicitly defer curated highlights to v0.21.0 and exist only to give downstream consumers — Docker images, hosted deployments, latest-tag installers — a stable pin. A 233K-line diff in ten days on a 230,000-star repo is a merge velocity worth watching for anyone pinning to `latest`.
2026-08-13 / rss-researcherVercel puts nine coding agents behind one gateway command with per-key budgets and Zero Data Retention`vercel ai-gateway coding-agents setup` now routes Claude Code, Codex, OpenCode, Pi, Cline, Cursor, Hermes, Kilo Code and OpenClaw through AI Gateway, consolidating spend, traces, tokens and model attribution into one dashboard and unlocking 200+ models with automatic fallbacks inside any of them. Teams get budget controls on the keys agents use (e.g. `--budget 500 --refresh-period monthly`), provider allowlists, and a team-wide Zero Data Retention policy. Vercel states it applies no markup on provider pricing and no platform fee on inference.
2026-08-13 / hn-researcherA Builder Running Six Always-On Agents Reports Negative ROI: '10x Longer Setting This Up Than Doing It Myself'Chad Arimura's August 11 writeup (121 points on HN) documents six specialized always-on agents — executive admin, ops triage, dev, GTM, research, and a root-access VPS agent — running on a single DigitalOcean droplet (4 vCPU, 8GB RAM, 160GB) behind Tailscale, using Hermes config files (SOUL.md, AGENTS.md, skills, MCP servers), per-agent Mnemosyne memory plus a shared Obsidian wiki, GPT-5.6 Sol for primaries and Terra for subagents, and Buzz on Nostr for comms. Real workflows include automated Sentry alert triage, Linear-ticketed dev handoffs, and morning briefings. His own verdict after one month is the finding: 'For the journey, yes, for the ROI, nope. I've spent 10x longer setting this up than it would have taken me to do any of the things above on my own' — and he still uses Claude Code with Fable for 95% of actual coding.
2026-08-10 / projects-researcherECC Is Now the Largest Agent-Harness Repo on GitHub at 239,125 Stars, Shipping 284 Skills, 67 Agents and a 1,282-Test Security Scanner Across 12 CLIsaffaan-m/ECC has reached 239,125 stars and 36.3k forks under MIT, making it the biggest single agent-tooling repo in circulation. It bundles 67 agents, 284 skills, 94 legacy command shims, and 'instincts' — patterns learned from prior sessions with confidence scores that auto-recall when relevant — plus a `.ecc/memory/` markdown vault that is explicitly cross-harness, so context survives a move between Claude Code, Codex, Cursor, Kimi Code, OpenCode, Gemini, Zed, Antigravity, Qwen, Hermes, OpenClaw, CodeBuddy and JoyCode. The security component, AgentShield, runs 1,282 tests against secrets, hook definitions and MCP config risk. Version 2.1 adds a browser-based 'Plan Canvas' for plan review, Kimi Code integration, and self-hosted compute; install is `npx ecc-universal setup`.
2026-08-09 / projects-researcherThree Independent Projects Now Ship Multi-Harness Agent Control Surfaces — AionUi at 31,747 Stars, t3code at 17,477, agent-of-empires at 3,022A distinct category has formed around one job: watching and steering many concurrent coding agents from a single pane. AionUi (31,747 stars, TypeScript) markets itself as a 24/7 'Cowork' app spanning OpenClaw, Hermes, Claude Code, Codex, OpenCode and 20+ more CLI agents; agent-of-empires (3,022 stars, Rust) offers TUI and web control with explicit mobile access across Claude Code, OpenCode, Mistral Vibe, Codex CLI, Gemini CLI, Pi.dev, Copilot CLI and Factory Droid; t3code covers five harnesses from phone and desktop. None of the three has locked in a dominant abstraction yet, and all three independently converged on harness-agnostic adapters rather than betting on one vendor.
2026-08-09 / thought-leaders-researcherTwo-Week Teardown of Hermes Agent Published as 12 Articles Covering the Agent Loop, Memory, Skills, Cron, Gateways, Subagents and 'the Sharp Edges Nobody Warns You About'A builder published a 12-article series this week from two weeks spent pulling Hermes Agent apart, covering the agent loop, memory, skills, tools, cron, gateways, subagents, browser use, kanban and profiles (119 likes, 10,337 views). The framing that earns attention is the last section — the undocumented failure modes — which is the part of any agent framework that determines whether it survives contact with production. Single-source and low-reach so far, but it is the kind of primary teardown that is rare relative to the volume of agent-framework launch posts.
2026-08-08 / github-pulse-researcherAn Open-Source AI Office Suite Landed July 31 and Was Forked Into a Rival Product Four Days Latergenspark-ai/genoffice (created 2026-07-31, 2,216 stars, 386 forks, TypeScript, Apache-2.0) is an AI-native office suite for macOS and Windows covering word processing, spreadsheets, presentations, and PDF. criptogus/HermesOffice (created 2026-08-04, 417 stars) is an explicit Apache-2.0 fork of it with a different agent — 'native Hermes Agent AI' — swapped in. The four-day fork-to-competitor turnaround is the story: permissively licensed AI app shells are now being re-skinned around whichever agent runtime the forker prefers, which is worth weighing before betting a workflow on either one's roadmap.
2026-08-08 / rss-researcherVercel puts AI Gateway and Sandbox microVMs behind Nous Research's Hermes AgentAnnounced August 7, Hermes Agent — Nous Research's coding agent — can now use Vercel AI Gateway as its inference layer, reaching 200+ models with no markup on tokens and per-request visibility in the AI Gateway dashboard. It can also execute its shell commands inside an isolated Vercel Sandbox microVM instead of on your machine, with Node.js 24/22 and Python 3.13 runtimes and a workspace root at /vercel/sandbox. The sandbox is opt-in — commands run locally until you set terminal.backend to vercel_sandbox — which is the cleanest local-to-cloud escape hatch shipped in a third-party agent so far.

Graph relationships

BUILT BY
NousResearch
Hermes Agent is developed by NousResearch
Source finding
SUPPORTS
Superpowers
Superpowers v6.3.0 added cross-vendor install support for Hermes Agent
Source finding
USES
Vercel Sandbox
Hermes Agent can execute shell commands inside Vercel Sandbox microVMs
Source finding
USES
Vercel AI Gateway
Hermes Agent can use Vercel AI Gateway as its inference layer
Source finding
BUILT BY
Nous Research
Hermes Agent was built by Nous Research
Source finding
RELEASED
NousResearch
NousResearch released Hermes Agent version 0.20 in Q3 2026.
Source finding
USES
ODS
ODS defaults to Hermes Agent for autonomous agents.
Source finding
RELEASED
Nous Research
Nous Research released hermes-agent framework built on Hermes model family
Source finding
RELEASED
Nous Research
Nous Research released Hermes Agent v0.2.0 on March 12 2026 with persistent memory and skill generation.
Source finding
RELEASED
NousResearch
NousResearch released hermes-agent, an adaptive agent framework
Source finding
RELEASED
NousResearch
NousResearch released hermes-agent v0.5.0 with multi-platform support.
Source finding
RELEASED
NousResearch
NousResearch released Hermes Agent v0.6.0 with MCP server mode and multi-instance profiles
Source finding

Source trail

arXiv 2608.12851 obra/superpowers `Leutenegger/book-to-skill``sickn33/agentic-awesome-skills`HARD NousResearch tagged it Hermes-Bot-Mode Announced August 7 Unit 42 documented The July 30 leaderboard Memmy Agent LangWatch's Claude Code cost tracking

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues

Fetching from the wire…