openclaw-amem 1.1.5 → 1.2.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md CHANGED
@@ -33,7 +33,7 @@ The first open-source A-MEM memory plugin for OpenClaw: dynamic graph linking, h
33
33
  - OpenClaw v2026.4+
34
34
  - Node.js 24 (18+ works; 24/26 supported)
35
35
  - Qdrant running on `:6333`
36
- - Anthropic API key (`ANTHROPIC_API_KEY`) or set `AMEM_LLM_BASE_URL` for a compatible proxy
36
+ - An LLM: `ANTHROPIC_API_KEY` by default, or any OpenAI-compatible provider see [LLM provider](#llm-provider)
37
37
 
38
38
  ## Installation
39
39
 
@@ -83,6 +83,15 @@ Add `openclaw-amem` to your allowed plugins and hook it into the `memory` slot:
83
83
  openclaw gateway restart
84
84
  ```
85
85
 
86
+ ## LLM provider
87
+
88
+ The plugin calls an LLM for note construction, linking, and evolution. Pick the backend with `AMEM_LLM_PROVIDER`:
89
+
90
+ - **`anthropic`** (default) — the Anthropic Messages API. Set `ANTHROPIC_API_KEY`.
91
+ - **`openai`** — the OpenAI Chat Completions API, which every OpenAI-compatible endpoint speaks. Set `AMEM_LLM_PROVIDER=openai`, point `AMEM_LLM_BASE_URL` at the endpoint, and set `AMEM_LLM_API_KEY` (or the standard `OPENAI_API_KEY`). Covers **OpenAI, DeepSeek, OpenRouter, Groq, Together**, and local servers (**Ollama, vLLM, LM Studio** — no key needed). Reasoning models (`o1`, `o3`, `gpt-5`) are handled automatically.
92
+
93
+ Choose the model with `AMEM_LLM_MODEL`. Full env-var reference and examples: **[amem.owo.lc/reference/configuration](https://amem.owo.lc/reference/configuration)**.
94
+
86
95
  ## Configuration Reference
87
96
 
88
97
  | Key | Type | Default | Description |
@@ -110,8 +119,8 @@ A memory plugin's job is to read configuration from the environment and send mem
110
119
 
111
120
  What it actually does — all of it declared in [`openclaw.plugin.json`](openclaw.plugin.json):
112
121
 
113
- - **Environment variables it reads** (its configuration surface, supplied by you): `AMEM_LLM_API_KEY`, `AMEM_LLM_BASE_URL`, `AMEM_LLM_MODEL`, `AMEM_COLLECTION`, `AMEM_DATA_DIR`, `AMEM_EVO_COUNTER_PATH`, `AMEM_REVIEW_DIR`, `AMEM_PROMPT_LOCALE`. No credential is bundled, hardcoded, or logged.
114
- - **Network destinations**: only your **local Qdrant** (`http://localhost:6333`) and your configured **LLM endpoint** (Anthropic by default, or `AMEM_LLM_BASE_URL`). It sends memory text/embeddings there to store and evolve notes — its stated purpose. It does not phone home.
122
+ - **Environment variables it reads** (its configuration surface, supplied by you): `AMEM_LLM_PROVIDER`, `AMEM_LLM_API_KEY`, `OPENAI_API_KEY`, `AMEM_LLM_BASE_URL`, `AMEM_LLM_MODEL`, `AMEM_COLLECTION`, `AMEM_DATA_DIR`, `AMEM_EVO_COUNTER_PATH`, `AMEM_REVIEW_DIR`, `AMEM_PROMPT_LOCALE`. No credential is bundled, hardcoded, or logged.
123
+ - **Network destinations**: only your **local Qdrant** (`http://localhost:6333`) and your configured **LLM endpoint** (Anthropic by default, or any OpenAI-compatible endpoint via `AMEM_LLM_PROVIDER=openai` + `AMEM_LLM_BASE_URL`). It sends memory text/embeddings there to store and evolve notes — its stated purpose. It does not phone home.
115
124
  - **Conversation content** is processed for memory only when you set `hooks.allowConversationAccess: true`. Keep Qdrant and review-output paths scoped to locations you control.
116
125
 
117
126
  ## Development