
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

Visual platform for building and deploying agentic workflows and knowledge pipelines

Code knowledge graph that gives coding assistants shared, source-linked context

Open-source RAG engine with a document pipeline, hybrid search and visual agent workflows

Self-hosted AI gateway routing many providers through one local endpoint with fallback

Web crawler and hosted API that turns URLs into LLM-ready Markdown or JSON

Gateway that trims context, remembers sessions and enforces rules for coding agents

Open-source SDK for building MCP apps and servers, with a hosted cloud for them

Build and run approved AI agent workflows: start runs, answer prompts, edit agents
Scan prompts for injection and PII, and audit LLM SDK usage from an MCP client
Open-source memory for AI agents that supersedes old facts and keeps costs flat
Not checked yetHosted human approvals and review pages for AI agents, with an audit trail
Open protocol server for signed agent messages carrying a token budget, mandate and price
Not checked yetSigned task envelopes that carry a token budget, mandate and price between agents
Not checked yetRead AI-visibility data and manage tracked prompts in Elmo, an open-source AEO tracker
Not checked yetShared memory for coding agents: proven fixes, known mistakes, skills and MCP discovery
Runs locallyPersistent shared memory for agents that recalls before acting and learns from outcomes
Not checked yetCheck app locale files and translate them into 46 languages from your editor
Runs locallyDrift, fairness and ISO 42001 evidence for AI systems, exposed as 197 MCP tools
Not checked yetRun the agents, teams and workflows of your Agentivity workspace from an AI assistant
Not checked yetExperimental local bridge to the Cicadas AI video API: models, quotes and job status
Runs locallySearch, install and bundle skills for AI coding agents from the LoopSkill marketplace
Not checked yetSearch a document set and return every relevant match with quotes
Not checked yetRead-only MCP access to Tracelane agent traces and guardrail verdicts for debugging
Runs locallyDaily human-verified catalog of free AI model API credits and token promotions
Not checked yetPolicy-enforced, permission-aware retrieval over your vector databases for agents
Runs locallyLet Zelinqa choose each next question so an assistant gathers information in fewer turns
Runs locallyResearch briefs built from verified quotations, refusing claims it cannot ground
Not checked yetMCP server for Algenta's self-hosted engine: governed queries, decisions and simulations
Not checked yet
Governance for company AI agents: pre-action checks, approvals and an audit trail over MCP
Not checked yet