Skip to content
Agent Search Engine.
Submit a tool
Menu

Alternatives · Autonomous Agents

Hermes Agent alternatives

These records overlap with Hermes Agent's recorded tasks and have the same product type. The selection uses task text, then information completeness; stars and sponsorship do not set the order. Check the specific capability you need before switching.

4 task-related records from 24 category candidates · all autonomous agents · how we rank

The product you're replacing

Hermes AgentAgentAutonomous Agents

Nous Research's self-improving AI agent that builds skills from experience and remembers you across sessions.

Costs not checked · 260k stars · Python · Open source · repository push Nov 2026

Visit Hermes Agent →Full Hermes Agent record

Hermes Agent's record says to avoid it if: You want a sandboxed assistant; it runs shell commands on the machine it is installed on.

Building one yourself? How to build an autonomous agent →

Task-related research candidates

CowAgentAgentOpen-source super AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-model, multi-channel. Lightweight, extensible, one-line install.Costs not checkedOpen sourcePython · recorded license: MITRecord checked · Recent push 48kGitHub stars

Shared terms in the records: memory, personal, self, skill. These text matches do not establish equivalent capabilities. The recorded use cases differ: Hermes Agent — People who want a persistent personal agent on their own server that improves the more it is used; CowAgent — An always-on personal assistant that controls your computer and chat platforms.

nanobotAgentLightweight, open-source AI agent for your tools, chats, and workflows.Costs not checkedOpen sourcePython · recorded license: MITRecord checked · Recent push 50kGitHub stars

Shared terms in the records: memory, self. These text matches do not establish equivalent capabilities. The recorded use cases differ: Hermes Agent — People who want a persistent personal agent on their own server that improves the more it is used; nanobot — A small, readable self-hosted agent framework with memory and MCP built in.

moltisAgentA secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, Telegram, WhatsApp, Discord, Teams, and MCP tools.Costs not checkedOpen sourceRust · recorded license: MITRecord checked · Recent push 2.9kGitHub stars

Shared terms in the records: memory, persistent, personal. These text matches do not establish equivalent capabilities. The recorded use cases differ: Hermes Agent — People who want a persistent personal agent on their own server that improves the more it is used; moltis — Running a persistent personal agent as a single Rust binary, with provider keys kept on your machine and every command executed in a sandboxed container.

deer-flowAgentAn open-source long-horizon SuperAgent harness that researches, codes, and creates.Harness plus model/tool-provider costsOpen sourcePython · recorded license: MITRecord checked · Recent push 85kGitHub stars

Shared terms in the records: memory, skill. These text matches do not establish equivalent capabilities. The recorded use cases differ: Hermes Agent — People who want a persistent personal agent on their own server that improves the more it is used; deer-flow — Orchestrating sub-agents, memory, and sandboxes through one extensible skill system.

Browse all autonomous agents →

Frequently asked

How were alternatives to Hermes Agent selected?
Recorded task topics and meaningful shared terms qualify same-type candidates in the same category. Results are ordered by that overlap, then information completeness and a stable identifier. Sponsorship and GitHub stars do not participate. The method can miss suitable tools whose records lack task information.
Does inclusion mean a tested replacement?
No. These are catalogue-based research candidates. Check current sources, costs, permissions and deployment requirements, then test your own task. ASE has not run a performance benchmark of this shortlist.