Skip to content

Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors

Rust

docs: note Hermes community plugin

AkitaOnRails4eddce7db78b
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 42b58917..a003c4f2 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -8,6 +8,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
## [Unreleased]
### Changed
+- Documented the community-maintained Hermes Agent plugin as a third-party
+ bridge rather than first-party ai-memory support, with compatibility and
+ secret-handling cautions ([#172]).
- `/admin/delete-workspace` now runs `purge_workspace` admission before
destructive work, reports filesystem partial failures in `files_failed`, and
notifies non-blocking mirrors after durable deletion; `/admin/rename-workspace`
diff --git a/README.md b/README.md
index f483d553..8c524168 100644
--- a/README.md
+++ b/README.md
@@ -35,6 +35,7 @@
| Grok Build CLI | Hooks | Lifecycle hooks via `install-hooks --agent grok` (`~/.grok/hooks/ai-memory.json`, Grok-specific hook bundle, native `--agent grok`). Capture works; no handoff injection — Grok ignores `SessionStart` stdout, so recover handoffs via MCP `memory_handoff_accept`. |
| Zero | Supported | `install-mcp --client zero` (native HTTP + bearer in `~/.config/zero/config.json`) + lifecycle hooks via `install-hooks --agent zero --apply` (exec-form native commands in `~/.config/zero/hooks.json`, JSON payload on stdin, no shell). Capture works incl. specialist (subagent) events; no handoff injection — Zero discards `sessionStart` stdout, so recover handoffs via MCP `memory_handoff_accept`. |
| VS Code Copilot | MCP-only | `.vscode/mcp.json` for Copilot agent mode; no lifecycle hooks (Copilot does not expose them yet). |
+| Hermes Agent | Community | A community-maintained [`ai-memory-hermes-plugin`](https://github.com/MrLuciano/ai-memory-hermes-plugin) is available. It is not part of ai-memory's first-party install surface; review its compatibility matrix, install/uninstall scripts, and secret handling before using it. |
| LLM/auth providers | Supported | Anthropic, OpenAI, OpenAI OAuth/Codex, GitHub Copilot, Gemini, OpenCode Zen/Go, OpenAI-compatible endpoints, and generic OIDC device auth for native hooks. |
| Embedding providers | Supported | OpenAI, Voyage, and Google Gemini. |
@@ -619,7 +620,7 @@ diagram, crate breakdown, schema notes, and invariants.
| [`docs/auto-scope.md`](docs/auto-scope.md) | `[auto_scope]` modes for shared servers: default single-slot routing, session-aware isolation, and multi-user `per_actor` behavior. |
| [`docs/macos.md`](docs/macos.md) | macOS install paths: native release binary (recommended), source build, the Docker wrapper, hook-platform notes, and current macOS limitations. |
| [`docs/windows.md`](docs/windows.md) | Windows install modes: full WSL2, native Windows with Docker Desktop, prebuilt native release zip, native source builds, and current hook/MCP harness caveats. |
-| [`docs/mcp-install.md`](docs/mcp-install.md) | Per-client MCP and lifecycle notes (Cursor, Claude Desktop, Gemini CLI, Antigravity CLI, OpenClaw, OMP, VS Code Copilot). |
+| [`docs/mcp-install.md`](docs/mcp-install.md) | Per-client MCP and lifecycle notes (Cursor, Claude Desktop, Gemini CLI, Antigravity CLI, OpenClaw, OMP, VS Code Copilot) plus community bridge guidance. |
| [`docs/deploy.md`](docs/deploy.md) | Homelab deploy: bin/deploy, bearer-token auth, pointers to the TLS guide. |
| [`docs/users.md`](docs/users.md) | **Multi-user attribution (v0.8).** Four-rung auth ladder, `ai-memory user add/list/expire/revive/rotate-token` walkthrough, backward-compat migration for pre-v0.8 installs, token storage rationale. |
| [`docs/https-via-proxy.md`](docs/https-via-proxy.md) | **HTTPS via a reverse proxy.** When you need TLS (multi-user, non-loopback) and when you don't (loopback / stdio). Copy-paste docker compose templates for Caddy + Let's Encrypt, Caddy + internal CA (LAN-only), Cloudflare Tunnel (no open ports), and external cert files; plus native-Caddy + nginx recipes. The "thinking you're secure when you're not" failure modes explicitly called out. |
diff --git a/docs/mcp-install.md b/docs/mcp-install.md
index 6cb1cacc..25af9c5e 100644
--- a/docs/mcp-install.md
+++ b/docs/mcp-install.md
@@ -55,6 +55,23 @@ calling `/hook` directly. For a third-party bridge that has its own
lifecycle vocabulary, keep the core `event` query param on one of
ai-memory's canonical events when possible:
+### Community-maintained Hermes Agent plugin
+
+ai-memory does not currently ship a first-party Hermes Agent installer,
+but a community-maintained
+[`ai-memory-hermes-plugin`](https://github.com/MrLuciano/ai-memory-hermes-plugin)
+is available. Treat it as a third-party bridge: verify the plugin's
+documented Hermes and ai-memory version matrix, install/update/uninstall
+behavior, platform coverage, and secret handling before enabling it on a
+live ai-memory server. In particular, bearer tokens and endpoint settings
+should stay in environment or local config references rather than generated
+plugin source files.
+
+The same lifecycle guidance below applies to Hermes or any other external
+bridge: map known events onto ai-memory's canonical hook events where
+possible, and use extension metadata for source-specific events instead of
+expanding ai-memory's stored event enum for one client.
+
```bash
curl -X POST \
'http://127.0.0.1:49374/hook?event=user-prompt&agent=other' \