hermes-agent

Hermes Agent is an AI agent framework/CLI plus a messaging gateway that supports interactive chat (TUI) and multi-platform messaging (e.g., Telegram/Discord/Slack/etc.). It provides tool-calling with a tools/toolsets system, persistent memory/skills, optional cron scheduling, and optional integration with MCP servers. It can run locally or on various hosted/back-end environments (e.g., Docker/SSH/Modal/Daytona) and supports switching LLM providers/models via CLI commands.

Evaluated Mar 29, 2026 (0d ago)
Homepage ↗ Repo ↗ Ai Ml ai-agent python tool-calling memory skills messaging-gateway mcp-integration telegram discord cron self-hosted
⚙ Agent Friendliness
31
/ 100
Can an agent use this?
🔒 Security
54
/ 100
Is it safe for agents?
⚡ Reliability
32
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
0
Documentation
60
Error Messages
0
Auth Simplicity
55
Rate Limits
10

🔒 Security

TLS Enforcement
80
Auth Strength
55
Scope Granularity
30
Dep. Hygiene
40
Secret Handling
60

The README links to a “Security” documentation section and mentions command approval, DM pairing, and container isolation, suggesting safety features exist. However, the provided text does not include concrete details for transport security requirements beyond general deployment expectations, nor does it specify how credentials are stored/handled at runtime or whether tool/action scopes are fine-grained. Hermes relies on external messaging platforms and external LLM providers; misconfiguration or overly broad tool permissions could increase risk.

⚡ Reliability

Uptime/SLA
0
Version Stability
50
Breaking Changes
40
Error Recovery
40
AF Security Reliability

Best When

You want a self-hosted, operator-controlled AI agent with persistent memory/skills and tool calling, optionally exposed through a messaging gateway, and you’re comfortable configuring providers/tools and running it as a process you manage.

Avoid When

You need a simple hosted API service with stable HTTP contracts, fine-grained OAuth scopes, and clearly documented API-level SLO/rate-limit behavior; the provided materials emphasize CLI/gateway usage rather than an HTTP developer platform.

Use Cases

  • Chat-based personal/work assistant with tool calling
  • Building and managing persistent “skills” and “memory” across sessions
  • Automated scheduled tasks with natural-language scheduling
  • Operating an agent via messaging platforms (e.g., Telegram/Discord) or CLI
  • Running agent workflows on remote/cloud backends with persistence/hibernate behavior
  • Integrating external MCP servers to extend capabilities

Not For

  • Use as a secure-by-default multi-tenant SaaS endpoint without additional operational controls
  • Environments requiring a formally specified REST/SDK contract for programmatic integrations
  • Teams needing clear, documented rate-limit and retry semantics at the API level (not evident in provided material)

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
No
SDK
No
Webhooks
No

Authentication

Methods: Configuration-driven provider API keys (e.g., Telegram/OpenAI/Anthropic/OpenRouter/etc. mentioned as allowlisted secrets during migration) Messaging gateway access control/pairing (described conceptually via security docs link)
OAuth: No Scopes: No

The README emphasizes configuration and provider/model switching rather than a dedicated OAuth flow for a Hermes API. Security-related behavior is referenced via a documentation link, but concrete authentication mechanics and scope granularity are not provided in the supplied text.

Pricing

Free tier: No
Requires CC: No

No pricing tiers are described for Hermes itself; it is presented as self-hosted with variable infrastructure/LLM costs.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • As an agentic system, tool calls and autonomous actions can have side effects; ensure command approvals/tool enablement are configured appropriately.
  • Backends like Modal/Daytona and messaging gateways may introduce integration-specific failure modes (networking, credentials, platform throttling).
  • Multi-provider LLM model switching requires correct provider configuration; misconfiguration may cause repeated failures without clear recovery guidance (not evidenced in provided text).
  • Long-running autonomous loops and memory/skills persistence increase the need for operational safety controls.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for hermes-agent.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-29.

5347
Packages Evaluated
21056
Need Evaluation
586
Need Re-evaluation
Community Powered