Hermes Agent today vs. yesterday?
Anonymous, one click, one vote per agent per day.
Pricing and cadence split Objective evenly — 0.2 of the total each.
Fewer than 3 votes on record → neutral 0.50, shown as provisional rather than as a real reading.
3 windows withheld for a thin sample — last 24 hours, last 7 days, last 30 days. Withheld, not averaged in as a zero.
No window clears the 5-post floor → neutral 0.50, shown as provisional.
2 windows withheld for a thin sample — last 7 days, last 30 days. Withheld, not averaged in as a zero.
Scoring v2 — recomputed live on every view from the pricing summary, the release log, the immutable vote log and the discussion extract. Never stored, never sold; there is no field in the data model that money can move.
Editorial layer · not in the score
The Honest Stack is our own opinion about what to actually use. It is deliberately not an input to the v2market signal — there is no editor’s term in the formula, and no field in the data model that carries one. Read it as a second, human opinion beside the number, never as part of it.
Entered at catalog seed — pending verification.
No pricing data yet — the pricing half of Objective stays neutral until it lands.
No pricing changes logged yet.
Daily net of anonymous better/same/worse votes. Bursts and over-cap votes are flagged automatically and excluded from every aggregate — they stay in the log, which is append-only.
No votes yet — cast the first one above.
No releases logged yet — the cadence half of Objective stays neutral until the radar fills in.
Objective, sourced facts about Hermes Agent pulled from the news record. These are context, not a score component — none is an input to the market signal.
Over 90% of Agent37's new signups are free plan users who host their personal Hermes/Openclaw/Claude Code etc on Agent37's cloud.
Users can host their personal Hermes on Agent37's cloud.
Users can host their personal Hermes/Openclaw/Claude Code on Agent37's cloud.
Users host their personal Hermes code on Agent37's cloud.
The digest · weekly
The most recent events linked to Hermes Agent, so you can read the record behind the number. These citations are context, not a score component — none of them is an input to the v2 formula above.
Launch HN: Agent37 (YC F26) – Low-cost agent sandboxes for running agents
Show HN: Television – an open source GUI for your agent harness
Show HN: Omnesis – A private knowledge layer for ChatGPT and other agents
DuoNeural/LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3-GGUF
DuoNeural/LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-GGUF
Free plan users of Agent37 host their personal Hermes/Openclaw/Claude Code etc on Agent37's cloud.
Over 90% of Agent37's new free plan users host their personal Hermes code/agents on Agent37's cloud.
Users host their personal Hermes/Openclaw/Claude Code on Agent37's cloud.
Free plan users of Agent37 host their personal Hermes on Agent37's cloud.
Television, an open source GUI, works with Hermes.
Television works with the Hermes agent harness.
Hermes is an agent harness that Television works with.
Television (a GUI for agent harnesses) works with Hermes.
Television works with Hermes agent harness.
Television, a GUI for agent harnesses, works with Hermes.
Hermes is an agent harness.
Hermes is an agent that can be connected to Omnesis's context layer.
Hermes can be connected to Omnesis.
Hermes (an agent) can be connected to Omnesis.
Hermes can be connected to the Omnesis context layer.
A model or project identified as 'DuoNeural/LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3-GGUF' is mentioned.
This 'Hermes-Agentic-Coder' model is described as 'agentic'.
This 'Hermes-Agentic-Coder' model is designed as a 'coder'.
A model incorporating 'Hermes-Agentic-Coder' exists with the full name 'DuoNeural/LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3-GGUF'.
A 'v3' version of this 'Hermes-Agentic-Coder' model is available.
A model named 'DuoNeural/LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3-GGUF' exists.
This 'Hermes-Agentic-Coder' model is available in the GGUF format.
Tincan cannot read what agents on Hermes write.
Hermes agents, when integrated with Tincan, can create shared rooms, exchange messages and files, and work together in real time.
Hermes agents can coordinate work with other agents (like Claude and Codex) in real time using Tincan.
Hermes is a type of AI agent harness.
Tincan cannot read what Hermes agents write when they use its services.
Messages and files exchanged by Hermes agents through Tincan are end-to-end encrypted.
Hermes agents can use Tincan to create shared rooms, exchange messages and files, and work together in real time.
Hermes is a harness for AI agents that can coordinate work with other agents in real time via Tincan.
AI agents using Hermes can exchange messages and files through Tincan.
Tincan cannot read what AI agents using Hermes write.
AI agents using Hermes can create shared rooms through Tincan.
Messages and files exchanged by AI agents using Hermes via Tincan are end-to-end encrypted.
AI agents using Hermes can coordinate work with other agents in real time via Tincan.
AI agents using Hermes can work together in real time through Tincan.
Hermes is a harness used for AI agents.
Agents using Hermes can use Tincan to create shared rooms, exchange messages and files, and work together in real time.
Agents across Hermes can coordinate work with agents on Claude and Codex using Tincan.
Tincan enables agents across different harnesses, including Hermes, to work together in real time.
Messages and files exchanged by agents on Hermes via Tincan are end-to-end encrypted.
Agents on Hermes can exchange messages and files using Tincan.
Hermes is a harness for agents.
Agents on Hermes can create shared rooms using Tincan.
Messages and files exchanged by agents using the Hermes harness via Tincan are end-to-end encrypted.
Agents using the Hermes harness can coordinate work with other agents in real time via Tincan.
Agents using the Hermes harness can exchange messages and files via Tincan.
Agents using the Hermes harness can create shared rooms via Tincan.
Agents using the Hermes harness can work together in real time via Tincan.
Hermes is a harness for AI agents.
Tincan enables agents (including those on Hermes) to create shared rooms, exchange messages and files, and work together in real time.
AI agents operating on Hermes can coordinate work with other agents using Tincan.
Agents on Hermes, when using Tincan, can exchange messages and files.
Agents on Hermes can use Tincan to coordinate work with other agents in real time.
Agents on Hermes, when using Tincan, can create shared rooms.
Tincan cannot read messages or files written by agents using the Hermes harness.
Agents on the Hermes harness can use Tincan to create shared rooms, exchange messages and files, and work together in real time.
Agents operating on the Hermes harness can coordinate work with agents on other harnesses (Claude, Codex) in real time through Tincan.
Tincan enables agents across different harnesses, including Hermes, to exchange messages and files.
Tincan enables agents across different harnesses, including Hermes, to create shared rooms.
Messages and files exchanged via Tincan by agents (including those on Hermes) are end-to-end encrypted.
Agents on Hermes can coordinate work with other agents in real time using Tincan.
There is a model named "DuoNeural/LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-GGUF".
The model "DuoNeural/LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-GGUF" is available in GGUF format.
The "Hermes-Agentic-Coder" model is an "Agentic Coder".
The model "DuoNeural/LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-GGUF" is in GGUF format.
There is an agentic coder model named "DuoNeural/LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-GGUF" available in GGUF format.
The "Hermes-Agentic-Coder" is associated with the model "LFM2.5-8B-A1B".
There is an AI model named "DuoNeural/LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-GGUF".
The model includes "Hermes-Agentic-Coder" in its name.
A model identified as "DuoNeural/LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-GGUF" exists.
Hermes was included in a 10-task GLM 5.3 harness benchmark along with Claude, OpenCode, pi, zcode, and 3code.
Hermes is included in a "10-task GLM 5.3 harness bench" alongside Claude, OpenCode, pi, zcode, and 3code.
Moadim.io, an agent scheduler, supports Hermes.
Moadim.io currently supports Hermes.
The moadim.io scheduler currently supports Hermes.
Moadim.io, a local Rust daemon scheduler for agents, currently supports Hermes.
Moadim.io currently supports Hermes as an agent.
The Moadim.io agent scheduler currently supports Hermes.
The agent scheduler Moadim.io currently supports Hermes.
There is a model identified as "jan1k/Tiel-Coder-35B-A3B-Genesis-Hermes-NVFP4-GGUF".
A model named "jan1k/Tiel-Coder-35B-A3B-Genesis-Hermes-NVFP4-GGUF" exists.
jan1k/Tiel-Coder-35B-A3B-Genesis-Hermes-NVFP4-GGUF is a model name that includes "Hermes".
Hermes can be tricked into running malware.
Hermes was tricked into running malware.
A researcher tricked Hermes (likely Hermes Agent) into running malware.
A researcher tricked Hermes into running malware.
Hermes installed unowned code inside corporate networks.
About 15% of issues in Hermes were related to communications.
Over 15% of issues in Hermes were related to communications.
15% or more of the issues observed in Hermes were related to communications.
15%+ of issues in Hermes were communication issues.
about 15%+ of issues in Hermes were related to communications.
about 15%+ of issues in Hermes were that of comms.
15%+ of issues in Hermes were related to communications.
Hermes is integrated into Relay, an interface accessible from phone, browser, or another computer.
Hermes can be accessed through Relay's interface from a phone, browser, or another computer.
Hermes is integrated into Relay's interface, alongside Claude Code, Codex, and OpenCode.
Hermes is integrated into Relay, an interface that unifies Claude Code, Codex, OpenCode, and Hermes, accessible from phone, browser, or another computer.
When used with Relay, Hermes is accessible from phones, web browsers, or other computers.
Relay brings Hermes into one interface that you can access from your phone, browser, or another computer.
Hermes is integrated into the Relay interface.
Hermes (Agent) is integrated into Relay, which provides a unified interface accessible from a phone, browser, or another computer.
Users can spin up Hermes agent on Maritime and keep it for free (along with OpenClaw and DeepSeek agent, up to three agents total).
Users can run Hermes agents for free on Maritime (up to three agents).
Hermes agents are available as templates on Maritime.
Users can run Hermes (Agent) for free through Maritime's template.
Hermes (Agent) is available as a template on Maritime.
When spun up via Maritime templates, Hermes agents can be kept for free (up to three agents).
Hermes is available as a template on Maritime.
Three agents, including Hermes, can be run for free forever on Maritime.
Hermes is available as a template on Maritime, a platform for running AI agents.
Users can run Hermes for free on Maritime, as one of three free agents available.
You can run Hermes for free on Maritime, as part of an offer for three free agents.
Hermes is available as a template to spin up on Maritime.
Hermes can be run for free on Maritime, along with OpenClaw and DeepSeek agents.
Hermes is one of the agents available as a template on Maritime.
Hermes can be run for free on Maritime (as part of a three-agent free limit).
Hermes (agent) can run 24/7.
Hermes runs 24/7.
Hermes agents can run 24/7.
Hermes can run 24/7.
Hermes, as an AI agent, is designed to run 24/7.
Hermes is provided as a base harness in HarnessRouter.
HarnessRouter is a canonical API for running Hermes as a managed agent harness for product backends.
Hermes (Agent) can be customized within HarnessRouter.
Hermes can be customized with harness instruction, MCP tools, and skills via HarnessRouter.
Hermes can be run as a product backend via HarnessRouter.
HarnessRouter provides routing to Hermes (Agent) as a base harness.
Hermes can be customized and configured with harness instruction, MCP tools, and skills within HarnessRouter.
HarnessRouter is a canonical API for running Hermes.
Users can configure harness instruction, MCP tools, and skills for Hermes within HarnessRouter.
HarnessRouter provides routing to Hermes as a base harness.
HarnessRouter allows configuration of harness instruction, MCP tools, and skills for Hermes (Agent).
Hermes can be customized within HarnessRouter.
Hermes is provided as a base harness in the Harnesses tab of HarnessRouter.
Hermes can be customized and configured with harness instruction, MCP tools, and skills when used with HarnessRouter.
HarnessRouter is an API for running Hermes as a managed agent harness.
Hermes is supported by HarnessRouter as a managed agent harness that can be used as a product backend.
Hermes can be run as a product backend via HarnessRouter, a canonical API for agent harnesses.
HarnessRouter provides a canonical API for running Hermes (Agent) as a product backend.
Hermes (Agent) is one of the managed agent harnesses supported by HarnessRouter.
Hermes's harness instruction, MCP tools, and skills can be customized and configured.
Hermes is a managed agent harness that can be run as a product backend via HarnessRouter.
Hermes is a managed agent harness.
Hermes Agent supports skill.
When used with SKI, Hermes Agent completes tasks and uses skill to talk about project updates, summaries, or queries using voice.
Hermes, as an agent, can complete tasks and use skills to talk about updates of a project or a summary or a query using voice.
Hermes can be used with SKI, a on-device voice coding application.
Hermes Agent can be used with SKI, an on-device voice coding application.
Hermes, when connected to SKI, can use skills to talk about a summary using voice.
When connected to SKI, Hermes (as an agent) completes tasks and uses skill to provide updates, summaries, or queries using voice.
Hermes is an agent that supports skill.
SKI, a voice coding application, can be used with Hermes.
Hermes, when connected to SKI, can use skills to talk about a query using voice.
Hermes, when connected to SKI, can use skills to talk about project updates using voice.
Hermes can be used with SKI, a voice coding application.
Hermes, when connected to SKI, can complete tasks.
Subjective claims voiced about Hermes Agent, each tagged with its polarity and linked to where it was said. Opinions from the record — never folded into the number.
Connecting Hermes to Omnesis gives the agent "context superpowers".
Omnesis gives 'context superpowers' to agents, including Hermes.
Omnesis gives Hermes (Agent) 'context superpowers'.
Hermes installed unowned code inside corporate networks
Hermes, as an AI agent, experienced communication bottlenecks.
Hermes experienced communication issues.