melvincarvalho · Oct 18, 2026 · Oct 18, 2026 · Oct 18, 2026 · Oct 18, 2026 · Oct 18, 2026
diff --git a/docs/contributing/openclaw.md b/docs/contributing/openclaw.md
@@ -53,6 +53,8 @@ Do not open a public issue. Report privately through GitHub security advisories
 ## Community
 
 - **Discord:** [discord.gg/clawd](https://discord.gg/clawd) (the official invite, from CONTRIBUTING.md)
+- **Forum:** [community.openclaw.ai](https://community.openclaw.ai), the official Discourse forum linked from openclaw.ai
+- **Foundation:** [openclaw.org](https://www.openclaw.org), launched 2026-07-08; Dave Morin is Chairperson and Vincent Koc Chief Architect ([people](https://www.openclaw.org/people), 2026-10-18). Press contact: press@openclaw.org
 - **Issues:** [github.com/openclaw/openclaw/issues](https://github.com/openclaw/openclaw/issues). The repository has GitHub Discussions turned off.
 
 ## See also

diff --git a/docs/guides/cost-management.md b/docs/guides/cost-management.md
@@ -61,7 +61,19 @@ Per million tokens (input / output), as of 2026-10-18, from [Anthropic pricing](
 | Claude Haiku 5.5 (prompt over 100K tokens) | `anthropic/claude-haiku-5-5` | $0.50 / $2.50 | $0.05 |
 | Legacy: Opus 4.6 to 4.8, Sonnet 4.6, Haiku 4.5 | | $5 / $25, $3 / $15, $1 / $5 | 0.1x input |
 
-For other providers, use the provider's own price page. OpenClaw's bundled estimate for `deepseek/deepseek-flash` is $0.30 / $1.20 at peak rates ([DeepSeek provider](https://docs.openclaw.ai/providers/deepseek)). Local models cost nothing per token.
+Other providers, per million tokens (input / output), as of 2026-10-18, from each provider's pricing page:
+
+| Model | Ref | Input / output | Source |
+|---|---|---|---|
+| GPT-6 Astra | `openai/gpt-6-astra` | $10 / $50 | [OpenAI](https://developers.openai.com/api/docs/pricing), Standard tier, short-context rates |
+| GPT-6.1 Sol | `openai/gpt-6.1-sol` | $2 / $10 | same |
+| GPT-6 Luna | `openai/gpt-6-luna` | $0.10 / $0.50 | same |
+| Gemini 3.1 Pro Preview (prompt up to 200K tokens) | `google/gemini-3.1-pro-preview` | $2 / $12 | [Google](https://ai.google.dev/gemini-api/docs/pricing), paid tier |
+| Gemini 4 Argon (not in the 2026.10.4 catalog) | | $2 / $10 until 2026-11-30, then $4 / $20 | same |
+| DeepSeek V4.1 Flash | `deepseek/deepseek-flash` | $0.30 / $1.20 at peak, $0.15 / $0.60 off-peak | [DeepSeek](https://api-docs.deepseek.com/quick_start/pricing), cache-miss input |
+| DeepSeek V4 Pro | `deepseek/deepseek-v4-pro` | $1.32 / $3.96 at peak, $0.66 / $1.98 off-peak | same |
+
+OpenAI charges more for long prompts (for example GPT-6.1 Sol $4 / $15). DeepSeek's peak hours are 01:00-04:00 and 06:00-10:00 UTC on weekdays. Two dated changes are worth knowing: Gemini 4 Argon, which the 2026.10.10 beta makes OpenClaw's default Gemini model, doubles in price on 2026-12-01; and DeepSeek bills its Search and Fetch APIs at $0.75 per 1,000 requests, which matters if DeepSeek serves your `web_search` (details in [Model Selection](/guides/model-selection#price-changes-ahead)). Local models cost nothing per token.
 
 ### Heartbeat costs {#heartbeat-costs}
 

diff --git a/docs/guides/hosting-providers.md b/docs/guides/hosting-providers.md
@@ -147,8 +147,8 @@ Simple single-plan pricing.
 
 Low-cost managed hosting on shared containers. It hosts both OpenClaw and Hermes.
 
-- **URL**: [agent37.com/openclaw](https://www.agent37.com/openclaw)
-- **Pricing** (as of 2026-10-18):
+- **URL**: [agent37.com/personal](https://www.agent37.com/personal) (the old `/openclaw` address redirects here). The [agent37.com](https://www.agent37.com) homepage now sells metered cloud sandboxes for agents; the OpenClaw and Hermes plans below are on `/personal`.
+- **Pricing** (as of 2026-10-18, [source](https://www.agent37.com/personal)):
 
 | Plan | Price | Specs |
 |------|-------|-------|
@@ -209,7 +209,7 @@ GDPR-compliant managed hosting on German VPS infrastructure.
 Managed hosting on a dedicated EU server for each customer, with OpenClaw or Hermes Agent installed on the same plans and prices.
 
 - **URL**: [oneclickclaw.io/openclaw](https://oneclickclaw.io/openclaw)
-- **Pricing**:
+- **Pricing** (regular prices, as of 2026-10-18, [source](https://oneclickclaw.io/openclaw)):
 
 | Plan | Monthly | Annual | Specs |
 |------|---------|--------|-------|
@@ -227,6 +227,7 @@ Managed hosting on a dedicated EU server for each customer, with OpenClaw or Her
 - **Payment**: Stripe in EUR (Visa, Mastercard, American Express, SEPA Direct Debit), monthly or annual, cancel any time
 - **GDPR**: Servers in Denmark, operated from Greece (EU)
 - **Hermes Agent**: Same plans and prices at [oneclickclaw.io/hermes](https://oneclickclaw.io/hermes)
+- **Temporary promotion**: on 2026-10-18 the site's page title advertised a "Halloween Sale from €9.99". The page text does not state the sale's terms or end date, and the regular prices above are unchanged, so the table keeps them.
 
 ### ClawBook.io {#clawbookio}
 
@@ -254,6 +255,7 @@ Managed OpenClaw hosting. Your own open-source AI agent gets a pod: a private, a
 
 - **URL**: [everpod.ai](https://everpod.ai)
 - **Price**: $29/month with up to $10 of model usage included each month, cancel anytime | Bigger plans from $59/month
+- **Developer pods** (as of 2026-10-18, [source](https://everpod.ai)): a separate product where you run the agent yourself over SSH through your own Tailscale network, with your own model plan or key and no model usage included. From $24/month (S: 4 vCPU, 8 GB RAM, 80 GB); M $42/month (8 vCPU, 16 GB, 160 GB); L $79/month (16 vCPU, 32 GB, 320 GB). Everpod says OpenClaw can be installed on one if you prefer to run it yourself
 - **Setup**: About 15 minutes; nothing to install, no technical knowledge needed
 - **Channels**: Telegram, Discord, Slack, WhatsApp, Signal and 20+ more
 - **Models**: OpenAI, Anthropic, Google, DeepSeek and more; usage capped by your plan; bring your own model key and nothing is added on top

diff --git a/docs/guides/memory-systems.md b/docs/guides/memory-systems.md
@@ -190,6 +190,8 @@ None of these is maintained by the OpenClaw project. Star counts and last-push d
 | [**PowerContext**](#powermem) | 1,337 | 2026-10 | Context service (formerly PowerMem) | Server / API |
 | [**Cognee**](#cognee) | 32,464 | 2026-10 | Knowledge graph memory | MCP / SDK |
 | [**Letta**](#letta) | 25,175 | 2026-09 | Stateful agent framework | SDK |
+| [**GBrain**](#gbrain) | 30,970 | 2026-10 | Agent "brain": knowledge pages, ingestion, scheduled consolidation | ClawHub bundle plugin / MCP |
+| [**agentmemory**](#agentmemory) | 29,640 | 2026-10 | Persistent memory server for coding agents | Native OpenClaw plugin (connector) / MCP |
 
 ---
 
@@ -324,6 +326,26 @@ MemPalace's published benchmark numbers were disputed after launch. Evaluate it
 
 ---
 
+### GBrain {#gbrain}
+
+**An opinionated agent "brain"** by Garry Tan: a store of pages about people, companies and ideas that the agent fills from meetings, email and other sources, with scheduled jobs that enrich and consolidate it overnight. The README describes it as the memory behind the author's own OpenClaw and Hermes deployments, and is candid that the always-on server setup is the costly path (an 8 GB+ server plus model tokens).
+
+- **Repo:** [garrytan/gbrain](https://github.com/garrytan/gbrain), MIT, created 2026-04-05; latest release v0.60.299.0 on 2026-10-18 (GitHub API)
+- **Integration:** per its README, a ClawHub bundle plugin (the repo ships `openclaw.plugin.json`) or an MCP server registered with OpenClaw; see its [OpenClaw guide](https://github.com/garrytan/gbrain/blob/master/docs/mcp/OPENCLAW.md). clawdocs has not tested it.
+- **Fit:** users who want the agent to build a large, curated knowledge base, not just recall past chats
+
+---
+
+### agentmemory {#agentmemory}
+
+**A local memory server for AI coding agents** (Claude Code, Codex, Copilot CLI, Cursor, Hermes, OpenClaw and any MCP client) that captures sessions and recalls them later.
+
+- **Repo:** [rohitg00/agentmemory](https://github.com/rohitg00/agentmemory), Apache-2.0, created 2026-02-25; latest release v0.9.30 on 2026-10-06 (GitHub API)
+- **Integration:** per its README, a connector installs a native OpenClaw plugin and skills, takes the memory slot and enables conversation access; replacing another memory plugin needs `--force`. MCP tools are opt-in. See its [OpenClaw setup](https://github.com/rohitg00/agentmemory/tree/main/integrations/openclaw). clawdocs has not tested it.
+- **Fit:** people who use several coding agents and want one memory shared between them
+
+---
+
 ## Integration Methods
 
 | Method | Setup | Examples |

diff --git a/docs/guides/model-selection.md b/docs/guides/model-selection.md
@@ -14,7 +14,7 @@ OpenClaw is model-agnostic. It ships provider plugins for the major cloud APIs,
 Model refs are always `provider/model`, for example `anthropic/claude-sonnet-5-5`. To see what your credentials can use, run `openclaw models list` (configured models) or `openclaw models list --all` (full catalog).
 
 :::tip Prices change
-Prices below are per million input/output tokens, **as of 2026-10-18**. Anthropic prices are from [Anthropic's pricing page](https://platform.claude.com/docs/en/about-claude/pricing). Where no source is given, check the provider's pricing page before you rely on a number.
+Prices below are per million input/output tokens, **as of 2026-10-18**, from the providers' own pages: [Anthropic](https://platform.claude.com/docs/en/about-claude/pricing), [OpenAI](https://developers.openai.com/api/docs/pricing) (Standard tier, short-context rates), [Google Gemini](https://ai.google.dev/gemini-api/docs/pricing) (paid tier) and [DeepSeek](https://api-docs.deepseek.com/quick_start/pricing). Where no source is given, check the provider's pricing page before you rely on a number.
 :::
 
 ---
@@ -27,12 +27,20 @@ Prices below are per million input/output tokens, **as of 2026-10-18**. Anthropi
 | Best default for agent work | `anthropic/claude-opus-5-5` (fresh Anthropic setups pick this) | $4 / $20 |
 | Balance of cost and quality | `anthropic/claude-sonnet-5-5` | $2 / $10 |
 | Cheap and fast | `anthropic/claude-haiku-5-5` | $0.10 / $0.50 up to 100K-token prompts; $0.50 / $2.50 above |
-| OpenAI default | `openai/gpt-6-astra` (also the built-in fallback when no model is configured) | See [OpenAI pricing](https://openai.com/api/pricing/) |
-| Google default | `google/gemini-3.1-pro-preview` (onboarding default in 2026.10.4; the next release moves to Gemini 4 Argon) | See [Gemini pricing](https://ai.google.dev/gemini-api/docs/pricing) |
-| Budget cloud | `deepseek/deepseek-flash` (V4.1 Flash) | About $0.30 / $1.20 at peak hours (OpenClaw's bundled estimate) |
+| OpenAI default | `openai/gpt-6-astra` (also the built-in fallback when no model is configured) | $10 / $50 |
+| Google default | `google/gemini-3.1-pro-preview` (onboarding default in 2026.10.4; the next release moves to Gemini 4 Argon, see [Price changes ahead](#price-changes-ahead)) | $2 / $12 up to 200K-token prompts; $4 / $18 above |
+| Budget cloud | `deepseek/deepseek-flash` (V4.1 Flash) | $0.30 / $1.20 at peak hours, half that off-peak (cache-miss input) |
 | Free, local | `ollama/qwen3:32b` or similar | $0 per token, your hardware |
 | One key for many providers | `openrouter/auto` | Pass-through pricing |
 
+### Price changes ahead {#price-changes-ahead}
+
+As of 2026-10-18, three dated price changes affect OpenClaw users:
+
+- **Gemini 4 Argon** (`gemini-4-argon`) costs $2 / $10 through 2026-11-30 and $4 / $20 from 2026-12-01, and is not on Google's free tier ([Gemini pricing](https://ai.google.dev/gemini-api/docs/pricing)). The 2026.10.10 beta makes Argon OpenClaw's default Gemini model ([v2026.10.10-beta.1](https://github.com/openclaw/openclaw/releases/tag/v2026.10.10-beta.1)). This site is pinned to 2026.10.4, whose catalog does not include Argon, so the refs on this page stay on `gemini-3.1-pro-preview`.
+- **Gemini 3.8 Flash and 3.6 Flash** cost $0.75 / $3.75 through 2026-12-31 and $1.50 / $7.50 from 2027-01-01.
+- **DeepSeek Search and Fetch** cost $0.75 per 1,000 successful requests. OpenClaw's DeepSeek plugin can serve `web_search`, which calls DeepSeek's Search API directly ([DeepSeek provider](https://docs.openclaw.ai/providers/deepseek#web-search)). DeepSeek's page says the server-side tool calls made through its Harness, Claude Code or Codex integrations are free until 00:00 Beijing time on 2026-11-01 and billed per request after that ([DeepSeek pricing](https://api-docs.deepseek.com/quick_start/pricing)).
+
 ---
 
 ## Recently added model support
@@ -85,18 +93,18 @@ The heartbeat is a scheduled agent turn, every 30 minutes by default. Run it on
 |---|---|---|
 | `anthropic/claude-fable-5-1` | Most capable Claude. Long turns on hard tasks. | $10 / $50 |
 | `anthropic/claude-opus-5-5` | Strong default for agent and coding work. Thinking is always on; use `/think low` to reduce it. | $4 / $20 |
-| `openai/gpt-6.1-sol` | OpenAI's top tier. Reasoning cannot be disabled. | See OpenAI pricing |
+| `openai/gpt-6.1-sol` | OpenAI's mid tier, below `gpt-6-astra` ($10 / $50). Same list price as Sonnet 5.5. Reasoning cannot be disabled. | $2 / $10 |
 | `anthropic/claude-sonnet-5-5` | Most coding at half the Opus price | $2 / $10 |
-| `deepseek/deepseek-v4-pro` | DeepSeek's onboarding default | See [DeepSeek pricing](https://api-docs.deepseek.com/quick_start/pricing) |
+| `deepseek/deepseek-v4-pro` | DeepSeek's onboarding default. No image input. | $1.32 / $3.96 at peak hours, half that off-peak |
 
 ### General chat and daily tasks
 
 | Model ref | Notes |
 |---|---|
 | `anthropic/claude-sonnet-5-5` | Good quality per dollar |
 | `anthropic/claude-haiku-5-5` | Cheapest Claude. Text and image input, 1M context. |
-| `openai/gpt-6-luna` | Lower-cost GPT-6 tier; check your account's catalog |
-| `google/gemini-3.7-flash` | Newest bundled Gemini Flash model in 2026.10.4. The `gemini-flash` alias still selects `google/gemini-3-flash-preview` |
+| `openai/gpt-6-luna` | Lowest-cost GPT-6 tier, $0.10 / $0.50 (the same as Haiku 5.5 on short prompts); check your account's catalog |
+| `google/gemini-3.7-flash` | Newest Gemini Flash model in the 2026.10.4 catalog. The `gemini-flash` alias still selects `google/gemini-3-flash-preview`. Google's pricing page now lists Gemini 3.8 Flash and 3.6 Flash ($0.75 / $3.75 until 2026-12-31, then $1.50 / $7.50) and no 3.7 Flash; the 2026.10.10 beta adds 3.8 Flash to the catalog |
 | `deepseek/deepseek-flash` | Budget option |
 
 ### Long context
@@ -286,9 +294,9 @@ Custom providers under `models.providers` are merged with the built-in catalog b
 | Provider | Current refs | Context | Pricing |
 |---|---|---|---|
 | Anthropic | `claude-fable-5-1`, `claude-opus-5-5`, `claude-sonnet-5-5`, `claude-haiku-5-5` | 1M | $0.10 / $0.50 (Haiku 5.5) to $10 / $50 (Fable 5.1), [source](https://platform.claude.com/docs/en/about-claude/pricing) |
-| OpenAI | `gpt-6-astra`, `gpt-6-sol`, `gpt-6.1-sol`, `gpt-6-luna`, `gpt-5.6-*` | Varies by model | [openai.com/api/pricing](https://openai.com/api/pricing/) |
-| Google | `gemini-3.1-pro-preview`, `gemini-3.7-flash`, `gemini-3.5-flash-lite` | 1,048,576 | [Gemini pricing](https://ai.google.dev/gemini-api/docs/pricing) |
-| DeepSeek | `deepseek-v4-pro`, `deepseek-v4-flash`, `deepseek-flash` | 1M | [DeepSeek pricing](https://api-docs.deepseek.com/quick_start/pricing) |
+| OpenAI | `gpt-6-astra`, `gpt-6-sol`, `gpt-6.1-sol`, `gpt-6-luna`, `gpt-5.6-*` | Varies by model | $0.10 / $0.50 (GPT-6 Luna) to $10 / $50 (GPT-6 Astra), short-context rates; long prompts cost more, [source](https://developers.openai.com/api/docs/pricing) |
+| Google | `gemini-3.1-pro-preview`, `gemini-3.7-flash`, `gemini-3.5-flash-lite` | 1,048,576 | $0.30 / $2.50 (3.5 Flash-Lite) to $2 / $12 (3.1 Pro Preview, up to 200K-token prompts), [source](https://ai.google.dev/gemini-api/docs/pricing) |
+| DeepSeek | `deepseek-v4-pro`, `deepseek-v4-flash`, `deepseek-flash` | 1M | $0.30 / $1.20 (Flash) to $1.32 / $3.96 (V4 Pro) at peak, half off-peak, [source](https://api-docs.deepseek.com/quick_start/pricing) |
 | xAI | `grok-4.7` and earlier 4.x | Varies | [xAI pricing](https://docs.x.ai/docs/models) |
 | OpenRouter | `openrouter/auto` or `openrouter/<author>/<slug>` | Varies | Pass-through, [openrouter.ai/models](https://openrouter.ai/models) |