hermes

13 repositories

NousResearch/hermes-agent

A self-improving agent that builds and refines its own skills over time — Hermes Agent, built by Nous Research, runs a learning loop that creates skills from experience, persists knowledge, searches past conversations, and builds a model of the user across sessions. It works with any LLM provider and runs anywhere from a $5 VPS to serverless infrastructure, reachable even via Telegram.

PythonAttention 37
★264,793
farion1231/cc-switch

One desktop app to juggle API providers across coding agents — A Rust/Tauri desktop app that lets you switch API providers for Claude Code, Codex, Gemini CLI, OpenCode and more with one click, and manage MCP, Skills, and Prompts centrally — skipping manual JSON/TOML/YAML config edits. Useful for developers running multiple AI coding agents side by side.

RustAttention 46
★155,874
paperclipai/paperclip

An open-source control center for coordinating AI agents at work — Paperclip is an open-source app for managing AI agents like Claude Code and Codex in daily workflows. It targets teams doing agent orchestration and multi-agent setups, offering MCP and agent-skills support, plus a cloud waitlist for broader rollout.

TypeScript🇺🇸 North AmericaAttention 41
★115,253
obsidianmd/obsidian-skills

Official Agent Skills bring Obsidian know-how to Claude, Codex, and more — Obsidian's official skills package teaches AI coding agents to work with the Obsidian CLI and open formats like Markdown, Bases, and JSON Canvas. Built to the Agent Skills spec, it installs into Claude Code, Codex, Cursor, or OpenCode, letting any compatible agent read and edit vaults correctly.

ShellAttention 45
★53,259
1Panel-dev/1Panel

A Linux panel that now doubles as a lightweight AI management hub — 1Panel, used by 2.5M+ self-hosters, combines Docker, LNMP stack and Webmin-style server management with new AI features like Ollama integration and agent tooling. It suits self-hosters and sysadmins wanting one open-source panel for both classic server admin and local AI model management.

Go🇨🇳 Greater ChinaAttention 26
★37,477
rohitg00/agentmemory

Give Claude, Copilot, Cursor and friends a shared memory — agentmemory adds persistent memory to coding agents like Claude Code, GitHub Copilot CLI, Cursor, Gemini CLI, Codex CLI and other MCP clients, built on the iii engine. It stops agents from forgetting context between sessions, so developers don't have to re-explain the same project details repeatedly.

TypeScript🇪🇺 EuropeAttention 40
★30,482
getpaseo/paseo

Paseo brings Claude Code, Codex, Copilot and more into one agent workspace — Paseo is an open source agentic development environment that unifies Claude Code, Codex, Copilot, OpenCode, Pi, Antigravity and Muse Code in one interface. It runs many agents in parallel, each in its own worktree across machines, with built-in orchestration so agents can spawn and talk to other agents. The same full app runs natively on desktop, web, CLI, and iOS/Android.

TypeScriptAttention 46
★24,470
screenpipe/screenpipe

Screenpipe records your work screen to surface automation targets — Screenpipe continuously captures screen and audio on company computers, then maps workflows to find tasks worth automating and feeds context to AI agents. Backed by YC S26, it's built local-first and privacy-conscious, aimed at teams wanting to understand and automate real work patterns rather than guess at them.

RustAttention 39
★22,480
EverMind-AI/Raven

A harness that orchestrates many AI agent harnesses at once — Raven acts as a Host Agent that wires together built-in and third-party agents (Claude, Codex, ChatGPT and others) into DAG-based workflows for complex tasks. It targets recursive self-improving, multi-agent setups rather than a single-model harness, aimed at developers building persistent, self-evolving agent ecosystems.

Python
★5,901
HarnessRouter/harnessrouter

One API to run Codex, Claude Code, Hermes and more agent harnesses — HarnessRouter CE is a self-hosted, Apache-2.0 gateway that unifies agent harnesses like Codex, Claude Code, Hermes, PI and DSH behind a single API with sessions, streaming, files, cancellation and failure handling. It implements the open Unified Harness Protocol (UHP) and is OpenAI Responses-compatible, aimed at teams building agent products who want to avoid harness-specific integration work.

PythonAttention 34
★4,391
awslabs/cli-agent-orchestrator

AWS Labs' orchestrator runs rival coding CLIs as cooperating agents — CAO runs a local cao-server that launches provider CLIs like Claude Code, Codex, Kiro, Copilot CLI, and more inside isolated tmux sessions, letting a supervisor delegate tasks to them in parallel or sequence. Each agent keeps its native authentication and capabilities as a full CLI process, making it useful for teams juggling multiple AI coding assistants.

Python🇺🇸 North AmericaAttention 55
★1,602
ai-timon/timon

A Self-Hosted AI Agent Team That Reuses Your CLI Logins — Timon runs a team of AI agents locally through CLI subscriptions you already have (like Claude Code), shipping reviewed code and pausing to ask before risky actions. It targets developers who want multi-agent automation without new API costs, running on Windows, macOS, and Linux as a plugin-extensible AGPL-licensed tool.

TypeScript🇪🇺 EuropeAttention 89
★621
prapaa-ai/agav

A self-contained CLI agent that tries to cut model-call waste — Agav is a terminal-native coding agent installable as a single binary, with no Node.js dependency. It supports multiple providers (OpenAI, OpenRouter, NVIDIA NIM, Ollama) and claims harness-level efficiency gains—caching context, bounding retries, and isolating subagent exploration—backed by a Terminal-Bench 2.1 cost study using GPT-5.

TypeScript🇮🇳 India
★195