Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors
Rust
docs: add Atlas Cloud compatibility recipe
AkitaOnRails371cfe95a419
diff --git a/CHANGELOG.md b/CHANGELOG.mdindex 5516f57e..bc7cb8d5 100644--- a/CHANGELOG.md+++ b/CHANGELOG.md@@ -8,6 +8,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0## [Unreleased]### Changed+- Documented Atlas Cloud through the existing `openai-compat` provider instead+ of adding a redundant provider type, including the endpoint, model, and API+ key mapping needed for deployment.- The native hook binary now drops any raw assistant-message field (ClaudeCode's `last_assistant_message` on `Stop`) before it can reach the localspool or the wire, and drains pre-existing spooled entries with the fielddiff --git a/README.md b/README.mdindex 00389245..aad3ad4c 100644--- a/README.md+++ b/README.md@@ -603,7 +603,7 @@ Recommended defaults:| `openai-oauth` | `gpt-5.5` | ChatGPT Pro/Plus/Codex backend via `ai-memory auth login openai-oauth`; no Platform API key. || `copilot` | `gpt-5.5` | GitHub Copilot Chat backend via `ai-memory auth login copilot` or `COPILOT_GITHUB_TOKEN`; requires a Copilot subscription. || `gemini` | `gemini-2.5-flash` | Google-hosted option with a generous free tier. |-| `openai-compat` | no default | OpenRouter, Ollama, vLLM, LM Studio, and other compatible endpoints. |+| `openai-compat` | no default | OpenRouter, Atlas Cloud, Ollama, vLLM, LM Studio, and other compatible endpoints. |`openai-oauth` stores a refresh token in `<data_dir>/auth.json` and talks tothe ChatGPT/Codex Responses backend, not `api.openai.com`. For Docker quick@@ -646,7 +646,7 @@ Embeddings are optional and separate from the LLM provider. Setyou want vector reranking in addition to FTS5 + graph-neighbor retrieval.See [`docs/install.md#llm-provider-tiers`](docs/install.md#llm-provider-tiers)-for env vars and Ollama/OpenRouter examples, and+for env vars and Ollama/OpenRouter/Atlas Cloud examples, and[`docs/llm-provider-comparison.md`](docs/llm-provider-comparison.md)for the empirical model comparison.diff --git a/docs/install.md b/docs/install.mdindex a22c411d..4e63c53d 100644--- a/docs/install.md+++ b/docs/install.md@@ -1046,7 +1046,7 @@ Advanced users with a pre-minted Copilot API token can setPass `--client-id` or set `AI_MEMORY_COPILOT_CLIENT_ID` if you operate your ownOAuth app.-### Self-hosted LLMs (Ollama / vLLM / LM Studio / OpenRouter)+### OpenAI-compatible providers (Ollama / vLLM / LM Studio / hosted APIs)```bashdocker run -d --name ai-memory \@@ -1069,6 +1069,20 @@ required. For OpenRouter (Kimi, DeepSeek, etc.):-e LLM_API_KEY=sk-or-v1-...```+[Atlas Cloud](https://www.atlascloud.ai/models/qwen/qwen3.5-flash) uses the+same provider; no Atlas-specific ai-memory provider is needed. Pass its API key+through the generic compatibility credential:++```bash+-e AI_MEMORY_LLM_PROVIDER=openai-compat+-e AI_MEMORY_LLM_BASE_URL=https://api.atlascloud.ai/v1+-e AI_MEMORY_LLM_MODEL=qwen/qwen3.5-flash+-e LLM_API_KEY="$ATLASCLOUD_API_KEY"+```++Replace the model with another current Atlas model id when needed. ai-memory+does not select a default for hosted compatibility endpoints.+Modern Ollama, vLLM, LM Studio, llama.cpp, and gateway endpoints may honourOpenAI-style `response_format=json_schema`. If the tolerant default parser failswith errors such as `did not contain a JSON object` or `serde: unknown variant`,