Skip to content

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

Rust

feat: default the Cursor provider to Grok 4.6

José Fernando Gomes Marcial1871f900bbd7
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 434bd16b..e80c8ae0 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -10,8 +10,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
### Added
- Added the `cursor` LLM provider. Consolidation calls the logged-in Cursor
Agent CLI (`agent --print --mode ask`) so a Cursor subscription can drive
- summaries without an API key. The default model is `composer-2.5-fast`;
- `AI_MEMORY_CURSOR_AGENT` overrides the binary. The provider never passes
+ summaries without an API key. The default model is `cursor-grok-4.6-high`
+ ("Grok 4.6"). `AI_MEMORY_CURSOR_AGENT` overrides the binary. The provider never passes
`--yolo` or `--force`, because the prompt is captured session text.
diff --git a/crates/ai-memory-llm/src/cursor_agent.rs b/crates/ai-memory-llm/src/cursor_agent.rs
index 52841e2d..2e9be51d 100644
--- a/crates/ai-memory-llm/src/cursor_agent.rs
+++ b/crates/ai-memory-llm/src/cursor_agent.rs
@@ -22,8 +22,9 @@ use crate::types::{ChatRequest, ChatResponse, Role};
/// Model used when `AI_MEMORY_LLM_MODEL` is unset.
///
-/// Fast Cursor model. Override with any id `agent --list-models` prints.
-pub const CURSOR_DEFAULT_MODEL: &str = "composer-2.5-fast";
+/// `agent --list-models` labels this id "Grok 4.6". Override with any other id
+/// from that list.
+pub const CURSOR_DEFAULT_MODEL: &str = "cursor-grok-4.6-high";
const MAX_STDOUT_BYTES: usize = 1024 * 1024;
const MAX_STDERR_BYTES: usize = 64 * 1024;
diff --git a/docs/install.md b/docs/install.md
index 240d68f0..cd1f76dd 100644
--- a/docs/install.md
+++ b/docs/install.md
@@ -1908,7 +1908,7 @@ If you set only the provider, ai-memory picks a sensible default:
| `AI_MEMORY_LLM_PROVIDER=openai-oauth` | `gpt-5.5` | ChatGPT/Codex backend. Run `ai-memory auth login openai-oauth` once; ai-memory stores the refresh token in `<data_dir>/auth.json` and refreshes access tokens automatically. Optional `AI_MEMORY_LLM_REASONING_EFFORT` (`none`/`minimal`/`low`/`medium`/`high`/`xhigh`/`max`/`ultra`/`persistent`) is mapped to each provider's native reasoning field; omit it to keep the model default. |
| `AI_MEMORY_LLM_PROVIDER=codex` | `gpt-5.6-luna` | Reuses only `access_token` and `account_id` from Codex's `auth.json`; token renewal is delegated to `codex app-server --stdio`. |
| `AI_MEMORY_LLM_PROVIDER=copilot` | `gpt-5.5` | GitHub Copilot Chat backend. ai-memory stores a GitHub user token in `<data_dir>/auth.json`, exchanges it for a short-lived Copilot API token, and refreshes before expiry. |
-| `AI_MEMORY_LLM_PROVIDER=cursor` | `composer-2.5-fast` | Cursor subscription via `agent --print --mode ask --trust`. No API key and no `--yolo`. Override the binary with `AI_MEMORY_CURSOR_AGENT`. Any id from `agent --list-models` works as `AI_MEMORY_LLM_MODEL`. |
+| `AI_MEMORY_LLM_PROVIDER=cursor` | `cursor-grok-4.6-high` | Cursor subscription via `agent --print --mode ask --trust`. No API key and no `--yolo`. This id is "Grok 4.6" in `agent --list-models`. Override the binary with `AI_MEMORY_CURSOR_AGENT`. Any other id from that list works as `AI_MEMORY_LLM_MODEL`. |
| `AI_MEMORY_LLM_PROVIDER=gemini` | `gemini-3.5-flash` | Google's hosted option with a generous free tier. ai-memory disables Gemini 3.5 Flash's default dynamic thinking so hidden thought tokens do not truncate strict JSON. Set `GEMINI_API_KEY` (or `GOOGLE_API_KEY`). |
| `AI_MEMORY_LLM_PROVIDER=opencode` | `mimo-v2.6-flash` | [OpenCode](https://opencode.ai) cloud API. Defaults to the **Go** endpoint, `opencode.ai/zen/go/v1` — a cost-optimised model subset. Published Responses models, including GPT-5.6 Luna and GPT-6 Luna, use `/responses`; supported Claude and Qwen Messages models use `/messages`. MiniMax M3/M2.7 and Qwen3.8 Max use Messages on Go and Chat Completions on Zen; Go Muse Contributor models use Responses. Changing the base URL reselects the transport and preserves request settings. See the [Go](https://opencode.ai/docs/go/#endpoints) and [Zen](https://opencode.ai/docs/zen/#endpoints) endpoint tables. For **Zen**'s full catalogue, set `AI_MEMORY_LLM_BASE_URL=https://opencode.ai/zen/v1` plus an `AI_MEMORY_LLM_MODEL` from it, such as `claude-sonnet-5-5`; the default model id is Go's. Requests identify ai-memory by version and reuse one session header across related attempts. Both endpoints take `OPENCODE_API_KEY` (key from `opencode.ai/auth`). Alias: `opencode-zen` — historical, and it selects Go like the others; the endpoint is chosen by the base URL, not the alias, with no automatic billing-product switch. |
| `AI_MEMORY_EMBEDDING_PROVIDER=openai` | `text-embedding-3-small` (1536-dim) | 5× cheaper than `-3-large` with marginal recall loss. |
diff --git a/docs/llm-providers.md b/docs/llm-providers.md
index b1255932..7f01c3df 100644
--- a/docs/llm-providers.md
+++ b/docs/llm-providers.md
@@ -47,7 +47,7 @@ Recommended defaults:
| `openai` | `gpt-5.4-mini` | Cheaper and faster hosted option. |
| `openai-oauth` | `gpt-5.5` | ChatGPT Pro/Plus/Codex backend via `ai-memory auth login openai-oauth`; no Platform API key. |
| `codex` | `gpt-5.6-luna` | Reuse the Codex CLI-owned `auth.json`; access-token refresh remains owned by `codex app-server`. |
-| `cursor` | `composer-2.5-fast` | Cursor subscription via the logged-in `agent` CLI. Runs `agent --print --mode ask` (read-only). Does not pass `--yolo`. |
+| `cursor` | `cursor-grok-4.6-high` | Cursor subscription via the logged-in `agent` CLI. Runs `agent --print --mode ask` (read-only). Does not pass `--yolo`. The default id is the one `agent --list-models` labels "Grok 4.6". |
| `copilot` | `gpt-5.5` | GitHub Copilot Chat backend via `ai-memory auth login copilot` or `COPILOT_GITHUB_TOKEN`; requires a Copilot subscription. |
| `gemini` | `gemini-3.5-flash` | Google-hosted option with a generous free tier. |
| `opencode` | `mimo-v2.6-flash` | OpenCode Go or Zen via `OPENCODE_API_KEY`. Go is the default endpoint; `AI_MEMORY_LLM_BASE_URL` selects Zen. Set `AI_MEMORY_LLM_MODEL` to an id the chosen endpoint serves. |
@@ -77,17 +77,17 @@ ai-memory llm-test --provider codex --model gpt-5.6-luna --structured --prompt "
```
`cursor` uses the Cursor Agent already logged in on this machine. Set
-`AI_MEMORY_LLM_PROVIDER=cursor`. The default model is `composer-2.5-fast`;
-any id from `agent --list-models` works. `AI_MEMORY_CURSOR_AGENT` overrides
-the binary. The provider writes the prompt into a temporary workspace and
-calls `agent --print --mode ask --trust`. It does not pass `--yolo` or
-`--force`: consolidation text is untrusted captured content, and those flags
-would allow tool execution.
+`AI_MEMORY_LLM_PROVIDER=cursor`. The default model is `cursor-grok-4.6-high`
+("Grok 4.6" in `agent --list-models`); any other id from that list works.
+`AI_MEMORY_CURSOR_AGENT` overrides the binary. The provider writes the prompt
+into a temporary workspace and calls `agent --print --mode ask --trust`. It
+does not pass `--yolo` or `--force`: consolidation text is untrusted captured
+content, and those flags would allow tool execution.
```bash
export AI_MEMORY_LLM_PROVIDER=cursor
-export AI_MEMORY_LLM_MODEL=composer-2.5-fast
-ai-memory llm-test --provider cursor --model composer-2.5-fast --prompt "Reply with OK"
+export AI_MEMORY_LLM_MODEL=cursor-grok-4.6-high
+ai-memory llm-test --provider cursor --model cursor-grok-4.6-high --prompt "Reply with OK"
```
Codex credential storage mode `file` is supported. `auto` works only when its