The kit is deliberately CLI-first: any harness that can run a shell command can use it. Specific notes per harness:
Two options, use both:
- Auto-recall on every prompt via the UserPromptSubmit hook - see claude-code-hook.md.
- A line in your CLAUDE.md or a skill so deliberate recall happens at task start - see agent-instructions.md.
The hook can inject a relevant excerpt from another local harness. Registering
mcp_server.py also gives Claude the explicit session_recall and
session_list tools.
The reliable path is a skill. Create
~/.hermes/skills/<category>/agent-memory/SKILL.md with standard skill
frontmatter (name, description stating when to use it) and the snippet from
agent-instructions.md as the body, with the absolute
paths to recall and remember on your machine. Hermes agents load skills
before substantial work, so the description is what triggers usage - make it
say "use at the start of substantial tasks to recall past fixes and findings".
mcp_server.py can also be registered if your Hermes version supports MCP
servers - consult the Hermes documentation for the current registration syntax
rather than guessing config keys.
Recent Hermes versions can run the same hook as a pre_llm_call shell hook.
The hook detects Hermes's wire format and emits native context. Keep the
explicit MCP tools as well so the agent can search deliberately.
Add the agent-instructions.md snippet to
~/.codex/AGENTS.md (or the project AGENTS.md) with absolute tool paths. Codex
runs the CLIs via shell like anything else. Register mcp_server.py as a stdio
MCP server when available so session recall is a first-class tool.
Register mcp_server.py as a stdio MCP server and set
AGENT_MEMORY_CALLER=grok for clear usage receipts. Add the standing rule from
agent-instructions.md to AGENTS.md, which Grok reads.
Do not install the Claude prompt hook as Grok auto-recall. Grok runs passive
UserPromptSubmit hooks, but ignores their stdout, so the returned context
never reaches the model. The supported continuity path is:
- Grok transcripts are indexed from
~/.grok/sessions session_recallis available through theagent-memoryMCP server- the standing instruction tells Grok when to call it
Verify all three. A configured MCP entry alone is not proof.
The contract is four commands: python3 ingest.py (rebuild documents),
recall "query" -k 5 (search documents), session-memory recall "query" -k 5
(search dialogue), and remember --source X --evidence Y "text" (write a
verified lesson). Wire them wherever your harness keeps standing instructions.
For harnesses that speak MCP but not shell, use mcp.md.