Hermes Agentmemory — Security skill for Claude Code
Pull-model episodic memory plugin for Hermes Agent.
How to install Hermes Agentmemory
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open MukundaKatta/hermes-agentmemory and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Hermes Agentmemory does
Pull-model episodic memory plugin for Hermes Agent. Real deletes, audit trace, BYO Claude. MIT.
Alternatives in Security
- Token Scan — Meme coin and token security scan — checks for rug pull vectors (hidden mint, honeypot, fee manipulation, LP l 3.8k ★
- Skill Coverage Audit — Trace codepaths in diffs, map against tests, auto-generate missing coverage — use before shipping PRs 2.8k ★
- Cross-Pollinate Hex MCP Servers — Diff-driven audit: find real transferable changes across hex-line-mcp, hex-ssh-mcp, hex-graph-mcp 238 ★
README
hermes-agentmemory
[](https://github.com/MukundaKatta/hermes-agentmemory/actions/workflows/test.yml) [](https://opensource.org/licenses/MIT) [](https://www.python.org/downloads/)
A drop-in [Hermes Agent](https://github.com/NousResearch/hermes-agent) memory plugin built on [agentmemory](https://github.com/MukundaKatta/agentmemory).
Pull-model episodic memory with real deletes and an audit trace. The point: Hermes Agent is good at remembering. This plugin gives it a memory layer that takes deletion seriously.
Why another memory plugin?
Hermes ships with several first-class memory backends (Mem0, Honcho, Hindsight, etc.). They consolidate in the background, which is the dominant pattern in agentic memory right now. That makes recall cheap and fast at the cost of two things:
- Deletes are not always real. Once an episode is baked into a derived summary, removing the original event leaves the summary intact.
- Memory injection is opaque. Background prefetch happens off the hot path; the user does not see exactly which past events were used until something goes wrong.
`agentmemory` flips both. It does no background work, every write is synchronous, deletes are immediate and complete, and every prefetch writes a trace record (`event_ids` + `summary` + `prompt`) to `$HERMES_HOME/agentmemory/trace.jsonl` so the user can audit what entered the prompt.
Install
This is a **standalone memory plugin**. Hermes Agent stopped accepting new built-in memory providers — see [CONTRIBUTING.md](https://github.com/NousResearch/hermes-agent/blob/main/CONTRIBUTING.md#memory-providers-ship-as-a-standalone-plugin). The official path is to drop the plugin into the user-plugins directory that Hermes discovers automatically.
# 1. Clone into
Related Skills
Claude Clean Context
Keep Claude Code's always-loaded context lean: deterministic memory guard-rail distiller + skills audit. Never
Hermes Memory Wiki
Memory Wiki dashboard plugin for Hermes Agent: browsable session-history wiki + persistent-memory audit panel
Sdlc Skill
End-to-end SDLC orchestrator skill for Claude Code. Drives one development task from brainstorm → plan → imple
Jev Skill Router
Jev-powered skill router & security auditor for any AI agent (Codex, Claude Code, OpenCode, Hermes): ONE cheap
Jgs Magic Sysmlv1 MCP
Bring Claude Code and any MCP agent to your live SysML v1 models in CATIA Magic: 130+ tools to query, audit, a
World Model MCP
world-model-mcp is a signed audit memory server for AI coding agents, delivered as an MCP tool. Every event Ed
Related Agents
Summary Writer
Background agent that processes a pending session summary. Reads the raw log, writes a narrative summary to th
Kanban Watcher
Read-only watcher (sonnet unless the caller sets a model) for one Hermes Kanban card or a small named set. It
Clive
Use to heal failing tests CI reported. Classifies each as isolation artefact, stale expectation or real bug an