nousresearch / hermes-agent
The agent that grows with you
github.com/nousresearch/hermes-agentIndexed at 13ce0c5Up to date with upstream
About this codebase
8,758 files and 100,728 symbols in 24 modules, led by Python (4,367 files) and TypeScript (2,339).
Built from the index
Code health
This codebase scores 5.3 out of 10 for code health, which we rate needs work. It also scores maintainability 6.8 and static performance 9.4 out of 10. The three are scored separately and never blended into one number. Risk is concentrated, as it usually is: 1,424 of 8,758 files are git hotspots, and they average 3.7 — which is where the fixes pay off most.
On the leaderboards:#6 of 6 Coding agents#40 of 44 Python repos
Do next
8 things worth doing this quarter, 6 of them now.
Worth planning
Update the decision “Fan out passthrough button presses to all live gateway sessions”: the code it governs has moved on
Agents and reviewers still follow it, so they are steered by a rule the code no longer keeps.
- status
- Accepted, drifting
Small effort, worth a checkDelete 86 unused symbols and files (1,380 lines)
Nothing in the graph reaches them, across 58 files; every reader and agent pays to skip them.
- symbols
- 86
- lines
- 1,380
- safe to delete
- Yes(inferred)
Medium effort
Improve what Repowise can see
Add a test coverage report
Without one, Repowise cannot tell tested code from untested code, so every test-related action says “unknown”.
- line coverage
- Unknown, no report
Small effort
Use nousresearch/hermes-agent in your agent
Point Claude Code, Cursor, Codex or VS Code at this repository. Your agent gets the index this page is built from: cited answers, callers, history and health for any file.
https://api.repowise.dev/mcp/nousresearch/hermes-agentOne command, run anywhere. Adds the server to your local Claude Code config.
Docsclaude mcp add --transport http repowise https://api.repowise.dev/mcp/nousresearch/hermes-agent \ --header "Authorization: Bearer rw_live_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
This repo is public, so anyone with a Repowise account and an API key can connect.
Try asking
- get_overview()
- get_answer("how is hermes-agent put together?")
- get_why("why is hermes-agent structured this way?")
Prefer local? pip install repowise && repowise init indexes your own checkout, no account needed.
Go deeper
- OverviewEverything the index found, what changed this week, commits and decisions.
- DocumentationModule-by-module documentation, 9,727 pages, 0 written by a model.
- ArchitectureDependency graph, layers and third-party dependencies.
- Code healthEvery file's score, the findings behind it, tests and refactoring plans.
- CommitsEach commit's effect on code health, with agent provenance.
- ContributorsWho owns what, and where one person holds most of the knowledge.
- DecisionsArchitectural decisions mined from commits and pull requests.
- Ask this codebaseSign inGrounded answers over the indexed code.
Maintain this repo? Claim the page
Sign in with GitHub and we check that you are an admin or maintainer of nousresearch/hermes-agent. Then add a badge to the README that links readers here.
Use this repo from Claude or ChatGPT
Add this URL as a custom connector and sign in with repowise when asked. No API key to copy.
https://api.repowise.dev/mcp/nousresearch/hermes-agentFor maintainers
Add a badge to your README
Every badge is public, cached, and updates on its own after every index. Nothing to install.
Repowise badge
Links to this page, with no score on it. Adding it also re-indexes the repo every week.
[](https://repowise.dev/repo/nousresearch/hermes-agent?src=badge_wiki)Code health badge
The repo's health score out of 10, from the latest index.
[](https://repowise.dev/repo/nousresearch/hermes-agent?src=badge_health)Code health card
A larger card with the score, its change since the last index, and when it was measured. The HTML version follows the reader's light or dark theme.
[](https://repowise.dev/repo/nousresearch/hermes-agent?src=badge_card)What is hermes-agent?
hermes-agent is a self-improving AI agent for conversations, tool use, automation, and work across terminal and messaging interfaces. It learns from experience by creating and improving skills, retaining knowledge, searching past conversations, and modeling users across sessions. hermes-agent is primarily written in Python, with TypeScript, JavaScript, shell, Rust, and C++ components.
Written by a model from the README and the index
Key features of hermes-agent
- hermes-agent creates skills from experience and improves them during use.
- hermes-agent provides a terminal interface with multiline editing, slash-command autocomplete, conversation history, interruption, redirection, and streaming tool output.
- hermes-agent connects conversations across Telegram, Discord, Slack, WhatsApp, Signal, and CLI through a single gateway process.
- hermes-agent searches past sessions with FTS5 and uses LLM summarization for cross-session recall.
- hermes-agent schedules unattended automations with a built-in cron scheduler and delivery to supported platforms.
- hermes-agent runs isolated subagents in parallel and supports Python scripts that call tools through RPC.
How nousresearch/hermes-agent works
Input enters through the hermes CLI for terminal conversations or through the gateway for messaging platforms. hermes_cli/main.py provides the CLI entry point, while gateway/run.py starts the messaging gateway. hermes_state.py manages agent state, including persistent knowledge and conversation context. The agent can use tools, create isolated subagents, and run Python scripts through RPC for multi-step work. hermes_cli/web_server.py supports web-server functionality associated with the CLI. apps/desktop/electron/main.ts is the desktop application's Electron entry point.
The agent that grows with you This page is a map of the nousresearch/hermes-agent repository, written primarily in Python, rebuilt from the source each time it is indexed. Repowise parses every symbol, computes a dependency graph, scores per-file code health from complexity, duplication, test coverage and churn, mines git history for hotspots and ownership, and lifts the architectural decisions into documentation you can read here or query through MCP.
The codebase has 8,758 files and 100,728 symbols in 24 modules, led by Python, TypeScript and JavaScript. Code health is 5.3 out of 10, rated needs work.
Use the links above to open each view, or connect this repository to your agent for grounded answers inside Claude, Cursor, Codex or VS Code.
Getting started with hermes-agent
- Reload the shell and start hermes-agent.
source ~/.bashrc # reload shell (or: source ~/.zshrc) - Start an interactive conversation.
hermes # start chatting!
Commands copied from the README
nousresearch/hermes-agent FAQ
What is hermes-agent?
hermes-agent is a self-improving AI agent for conversations, tools, automation, and work across terminal and messaging interfaces. It creates skills from experience and retains knowledge across sessions.
How does hermes-agent work?
hermes-agent accepts input through its CLI or messaging gateway, then uses tools, memory, skills, and subagents to perform work. hermes_state.py manages state, while gateway/run.py and hermes_cli/main.py provide gateway and CLI entry points.
How do I install hermes-agent?
Install hermes-agent with the Linux, macOS, or WSL2 shell installer, or use the PowerShell installer on native Windows. After installation, run hermes to start chatting.
What language is hermes-agent written in?
hermes-agent is primarily written in Python. The repository also includes TypeScript, JavaScript, shell, Rust, and C++ code.
How is the hermes-agent code organized?
hermes-agent is organized into modules including hermes_cli, apps, skills, optional-skills, plugins, ui-tui, website, and tests. Key runtime files include hermes_cli/main.py, gateway/run.py, hermes_state.py, and hermes_cli/web_server.py.
Who is hermes-agent for?
hermes-agent is for people who want an AI agent that can work through a terminal or messaging platforms, retain context, create skills, schedule tasks, and run tools across different environments.
What license does hermes-agent use?
hermes-agent uses the MIT license.
Answers written by a model from the README and the index