diff --git a/AGENTS.md b/AGENTS.md
new file mode 100644
index 0000000..dcd69a7
--- /dev/null
+++ b/AGENTS.md
@@ -0,0 +1,69 @@
+# AGENTS.md — Mem0 Local Hermes Plugin
+
+## Structure
+
+Single-file plugin: `__init__.py` contains the `Mem0LocalMemoryProvider` class. HTTP client in `client.py`. Manifest in `plugin.yaml`.
+
+## Key Commands
+
+```bash
+# Install from repo
+hermes plugins install ARIA/mem0-local-hermes-plugin
+
+# Install from local path (development)
+hermes plugins install /path/to/mem0-local-hermes-plugin
+
+# Activate memory provider
+hermes memory mem0-local
+
+# Restart gateway after changes
+hermes gateway restart
+
+# Verify Mem0 server
+curl http://localhost:8000/health
+```
+
+## Configuration
+
+**Two-tier config (JSON overrides env):**
+
+1. `~/.hermes/.env` — Primary config
+2. `~/.hermes/mem0-local.json` — Optional overrides
+
+**Required env vars:**
+- `MEM0_BASE_URL` — Mem0 server URL (default: `http://localhost:8000`)
+- `MEM0_USER_ID` — User identifier (default: `hermes-user`)
+
+**Optional env vars:**
+- `MEM0_AGENT_ID` — Agent identifier (default: `hermes`)
+- `MEM0_PREFETCH_LIMIT` — Max memories to prefetch (default: `3`)
+- `MEM0_PREFETCH_SCORE_THRESHOLD` — Min similarity % (default: `60`)
+
+## Architecture
+
+**Memory injection flow:**
+1. `queue_prefetch()` — Spawns background thread on user message
+2. `prefetch()` — Returns cached result next turn
+3. `pre_llm_call` hook — Sync prefetch for immediate injection (fallback context)
+4. `sync_turn()` — Non-blocking server-side fact extraction
+
+**Circuit breaker:** 5 consecutive failures → 120s cooldown.
+
+**Dual-context registration:**
+- `register_memory_provider()` — When installed in `plugins/memory/`
+- `register_tool()` + `pre_llm_call` hook — When installed in `~/.hermes/plugins/`
+
+## Tools
+
+| Tool | Purpose |
+|------|---------|
+| `mem0_profile` | Get all stored memories |
+| `mem0_search` | Semantic search with optional reranking |
+| `mem0_conclude` | Store fact verbatim |
+| `mem0_delete` | Delete memory by ID |
+
+## Dependencies
+
+- `requests` (via `pip_dependencies` in `plugin.yaml`)
+- Hermes gateway with memory provider support
+- Self-hosted Mem0 server (Docker image: `mem0ai/mem0:latest`)
diff --git a/README.md b/README.md
index 0e0660e..1df98a0 100644
--- a/README.md
+++ b/README.md
@@ -42,10 +42,7 @@ Self-hosted Mem0 memory provider for Hermes-Agent. Provides semantic memory sear
    curl http://localhost:8000/health
    ```
 
-   Your setup uses port 8889:
-   ```bash
-   curl http://10.0.0.150:8889/health
-   ```
+   Adjust the URL/port as needed for your setup.
 
 ## Installation
 
@@ -98,35 +95,30 @@ Set in `~/.hermes/.env`:
 | `MEM0_BASE_URL` | Local Mem0 server URL | `http://localhost:8000` |
 | `MEM0_USER_ID` | User identifier | `hermes-user` |
 | `MEM0_AGENT_ID` | Agent identifier | `hermes` |
+| `MEM0_PREFETCH_LIMIT` | Max memories to prefetch before LLM call | `3` |
+| `MEM0_PREFETCH_SCORE_THRESHOLD` | Min similarity score % to include memory (0-100) | `60` |
 
 Example:
-```env
-MEM0_BASE_URL=http://10.0.0.150:8889
-MEM0_USER_ID=henry_hofmann
-MEM0_AGENT_ID=hermes
-```
+   ```env
+   MEM0_BASE_URL=http://localhost:8000
+   MEM0_USER_ID=my-user
+   MEM0_AGENT_ID=hermes
+   MEM0_PREFETCH_LIMIT=3
+   MEM0_PREFETCH_SCORE_THRESHOLD=60
+   ```
 
 ### Method 2: Config File (Optional Overrides)
 
 Create `~/.hermes/mem0-local.json` to override specific settings:
 ```json
 {
-  "base_url": "http://10.0.0.150:8889",
-  "user_id": "henry_hofmann",
+  "base_url": "http://localhost:8000",
+  "user_id": "my-user",
   "agent_id": "hermes",
   "rerank": true,
-  "timeout": 10.0
-}
-```
-
-Example for your setup:
-```json
-{
-  "base_url": "http://10.0.0.150:8889",
-  "user_id": "henry_hofmann",
-  "agent_id": "hermes",
-  "rerank": true,
-  "timeout": 10.0
+  "timeout": 10.0,
+  "prefetch_limit": 3,
+  "prefetch_score_threshold": 60
 }
 ```
 
@@ -218,7 +210,7 @@ After 5 consecutive API failures, the plugin pauses requests for 120 seconds to
 
 ### Connection issues
 
-If your Mem0 server is on a different machine (like your 10.0.0.150):
+If your Mem0 server is on a different machine:
 - Ensure firewall allows connections on port 8889
 - Verify the server binds to 0.0.0.0, not just localhost
 - Check network routing between Hermes-Agent and Mem0 server
diff --git a/client.py b/client.py
index 31fe6f1..cde4c10 100644
--- a/client.py
+++ b/client.py
@@ -1,6 +1,6 @@
 """Local Mem0 server HTTP client.
 
-Based on OpenAPI spec from http://10.0.0.150:8889/openapi.json
+Based on Mem0 server OpenAPI specification.
 
 Endpoints:
 - POST /add - Add memory