
hermes-agent
AgentOpen-source self-improving agent with memory, scheduling and many chat gateways
- Freemium
- Open-source agent
- 264K GitHub stars
- AI models and LLM tooling

Open-source self-improving agent with memory, scheduling and many chat gateways

Free open-source AI studio for local chat, image, video and coding, with optional cloud
Stops AI coding agents stuck in error loops and tracks token spend across tools
Free MCP server for AI model retirement dates, repo model scans and usage-cost checks
Runs locallyMulti-model review council and parallel model sidecar for Claude Code
Runs locallyOne long-term memory store shared across Claude Code, Cursor and your agents
Runs locallyOffline scan of local AI agent folders for heartbeat cost, exposed keys and planted memory
Runs locallyTurn scripts into voiceover audio with matching SRT and VTT subtitles
Runs locallySee where your coding agent's tokens and money went, with cache-safe fixes
Runs locally
Rust build of Microsoft's markitdown that turns documents and web pages into Markdown
Runs locallyShared mailbox, handoffs and file-clash warnings for your coding agents
Runs locallySearch open AI model files with recorded SHA-256 hashes and license labels
Not checked yetGive an assistant a voice: text to speech in about 190 voices, cloud or local
Runs locallySource-linked AI API prices, cost estimates, model comparisons and price changes
Runs locallySeven-tool proof loop that authorizes agent actions and records tamper-evident evidence
Runs locallyPicks the minimum code an LLM needs to review a git diff, locally and deterministically
Runs locallyHeartbeat and tokens-per-second monitoring for home Ollama, llama.cpp and vLLM servers
Not checked yetMCP gateway to MeshMarket, where agents rent each other's capabilities per call
Not checked yetMCP server that supplies the template and checker for building single-file AI agents
Not checked yetFree challenge that checks agents' claims against signed receipts of their calls
Runs locallyLets coding agents generate media and build node workflows in the Infiknit desktop app
Runs locallyMCP server that grades an AI agent's conversations on 18 reliability tests
Runs locally