Agentmemory Config
Look up all 34 AGENTMEMORY_* environment variables and where agentmemory reads config from ~/.agentmemory/.env.
Overview
agentmemory-config is an agent skill most often used in Build (also Ship, Operate) that documents all 34 AGENTMEMORY_* settings and how agentmemory loads them.
Install
npx skills add https://github.com/rohitg00/agentmemory --skill agentmemory-configWhat is this skill?
- Autogenerated catalog of 34 recognized AGENTMEMORY_* variables from src/
- Documents ~/.agentmemory/.env loading without export prefix
- Covers provider, session, graph weight, auto-compress, inject-context, and viewer URLs
- Regenerate via npm run skills:gen—do not hand-edit the AUTOGEN env block
- Excludes internal double-underscore marker variables from the public list
- 34 recognized AGENTMEMORY_* variables in autogenerated catalog
Adoption & trust: 3 installs on skills.sh; 21.9k GitHub stars; trending (+300% hot-view momentum).
What problem does it solve?
You enabled AgentMemory but sessions, MCP blocks, or viewers misbehave because env vars are undocumented or drift from the codebase.
Who is it for?
Solo devs standardizing AgentMemory across Claude Code, Cursor, or Codex setups with repeatable env files.
Skip if: Teams not using the rohitg00/agentmemory project—this is package-specific reference, not generic RAG memory theory.
When should I use this skill?
When configuring, debugging, or documenting AgentMemory environment and ~/.agentmemory/.env settings.
What do I get? / Deliverables
You get an authoritative variable list and load paths so you can set ~/.agentmemory/.env and regenerate docs after code changes.
- accurate env variable reference
- regeneration instructions for maintainers
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Agent memory configuration is set up while wiring agent tooling, then reused across Ship and Operate when tuning sessions. agent-tooling is the canonical shelf for env contracts that define how persistence, MCP blocks, and viewers behave.
Where it fits
Set AGENTMEMORY_PROVIDER and AGENTMEMORY_INJECT_CONTEXT before first local agent run.
Verify AGENTMEMORY_MCP_BLOCK and Copilot settings match team policy before merging agent config changes.
Point AGENTMEMORY_VIEWER_URL and probe timeouts at staging while debugging stale index drops.
How it compares
Generated env reference for one product, not a journey-wide planning methodology.
Common Questions / FAQ
Who is agentmemory-config for?
Builders and operators running AgentMemory who need a complete, code-synced list of configuration variables.
When should I use agentmemory-config?
Use it in Build while wiring agent-tooling, in Ship when debugging agent sessions before release, and in Operate when tuning monitoring, viewer URLs, or compression on production machines.
Is agentmemory-config safe to install?
It is read-only reference material; review the Security Audits panel on this page and avoid placing secrets in chat—use AGENTMEMORY_SECRET via env files locally.
SKILL.md
READMESKILL.md - Agentmemory Config
# agentmemory configuration reference Generated by scanning `src/` for `AGENTMEMORY_*` usage. Do not edit the block below by hand; run `npm run skills:gen` after adding or removing a variable. Internal markers ending in two underscores are excluded. <!-- AUTOGEN:env START - generated by scripts/skills/generate.ts, do not edit by hand --> Configuration is read from the environment and from `~/.agentmemory/.env` (no `export` prefix). 34 recognized variables: - `AGENTMEMORY_AGENT_SCOPE` - `AGENTMEMORY_ALLOW_AGENT_SDK` - `AGENTMEMORY_AUTO_COMPRESS` - `AGENTMEMORY_COMMIT_SHA` - `AGENTMEMORY_COPILOT_MCP_BLOCK` - `AGENTMEMORY_CWD` - `AGENTMEMORY_DEBUG` - `AGENTMEMORY_DROP_STALE_INDEX` - `AGENTMEMORY_EXPORT_ROOT` - `AGENTMEMORY_FOLLOWUP_WINDOW_SECONDS` - `AGENTMEMORY_FORCE_PROXY` - `AGENTMEMORY_GRAPH_WEIGHT` - `AGENTMEMORY_III_CONFIG` - `AGENTMEMORY_III_VERSION` - `AGENTMEMORY_IMAGE_EMBEDDINGS` - `AGENTMEMORY_IMAGE_STORE_MAX_BYTES` - `AGENTMEMORY_INJECT_CONTEXT` - `AGENTMEMORY_LLM_TIMEOUT_MS` - `AGENTMEMORY_MCP_BLOCK` - `AGENTMEMORY_PROBE_TIMEOUT_MS` - `AGENTMEMORY_PROJECT_NAME` - `AGENTMEMORY_PROVIDER` - `AGENTMEMORY_REFLECT` - `AGENTMEMORY_SDK_CHILD` - `AGENTMEMORY_SECRET` - `AGENTMEMORY_SESSION_ID` - `AGENTMEMORY_SLOTS` - `AGENTMEMORY_SUPPRESS_COST_WARNING` - `AGENTMEMORY_TOOLS` - `AGENTMEMORY_URL` - `AGENTMEMORY_USE_DOCKER` - `AGENTMEMORY_VERBOSE` - `AGENTMEMORY_VIEWER_HOST` - `AGENTMEMORY_VIEWER_URL` <!-- AUTOGEN:env END --> --- name: agentmemory-config description: agentmemory configuration, environment variables, ports, and feature flags. Use when enabling a feature, changing ports, setting an API key, configuring auth, or explaining why a feature is off by default. user-invocable: false --- agentmemory reads configuration from the environment and from `~/.agentmemory/.env` (one `KEY=value` per line, no `export` prefix). Restart the server after changing it. ## Quick start Enable richer memory and set a provider key in `~/.agentmemory/.env`: ```env ANTHROPIC_API_KEY=sk-ant-... AGENTMEMORY_AUTO_COMPRESS=true AGENTMEMORY_INJECT_CONTEXT=true ``` ## Defaults worth knowing - No API key is required. Without one, agentmemory runs zero-LLM with BM25 plus local embeddings. - Token-spending features ship OFF on purpose: `AGENTMEMORY_AUTO_COMPRESS` (LLM summaries) and `AGENTMEMORY_INJECT_CONTEXT` (auto context injection) both cost tokens proportional to tool-use frequency. - Tool visibility: `AGENTMEMORY_TOOLS=all` (default) or `core` for the lean set. - Auth: set `AGENTMEMORY_SECRET` to require `Authorization: Bearer` on the REST API. ## Ports REST is the anchor at 3111. Streams = N+1 (3112), viewer = N+2 (3113), engine = N+46023 (49134). Relocate the whole block with `--port <N>` or `--instance <N>`. ## See also - agentmemory-rest-api for how the secret is used. - agentmemory-architecture for the port quartet rationale. ## Reference The full recognized-variable list lives in REFERENCE.md, generated by scanning `src/`.