Skip to content

Open-source platform for 3D AI agents. Turn text or a photo into a rigged, animated GLB avatar, give it an LLM brain, memory and a wallet, and embed it anywhere with one web component. Remote MCP server, x402 payments, Three.js, browser-native.

fix(style): replace banned em-dashes and a comment the rules check read as code in the pushed range

nirholasfe6dafa8da67
diff --git a/ARCHITECTURE.md b/ARCHITECTURE.md
index e8003fc87..78763d12d 100644
--- a/ARCHITECTURE.md
+++ b/ARCHITECTURE.md
@@ -3292,7 +3292,7 @@ three.ws exposes MCP tools across **8 remote HTTP servers** + **34 stdio/npm ser
- **Agent Wallet — `POST /api/mcp-agent`** (OAuth + x402 from agent wallet): `getting_started`, `wallet_status`, `find_services`, `pay_and_call`(variable), `provision_wallet`, `monetize_endpoint` (6).
- **Bazaar — `POST /api/mcp-bazaar`**: `getting_started`, `search_services`, `browse_services`, `get_service` (4).
- **IBM Granite — `POST /api/ibm-mcp`** (x402 USDC Base/Solana): `ibm_granite_getting_started`, `ibm_granite_chat`($0.02), `ibm_granite_code`($0.025), `ibm_granite_embed`($0.005), `ibm_granite_analyze`($0.04), `ibm_granite_forecast`($0.05) (6).
-- **Pump.fun — `POST /api/pump-fun-mcp`** (mostly free; 4 gated tools <!-- mcp-count-ignore --> need Bearer or $0.001 x402): `search_tokens`, `get_token_details`, `get_bonding_curve`, `get_token_trades`, `get_trending_tokens`, `get_new_tokens`, `get_graduated_tokens`, `get_king_of_the_hill`, `get_creator_profile`, `get_token_holders`, `pumpfun_vanity_mint`*, `pumpfun_watch_whales`*, `pumpfun_list_claims`, `pumpfun_watch_claims`*, `pumpfun_first_claims`, `sns_resolve`, `sns_reverseLookup`, `social_cashtag_sentiment`, `kol_leaderboard`, `pumpfun_quote_swap`, `social_x_post_impact`, `get_coin_intel`, `get_oracle_conviction`, `pumpfun_upload_metadata`*, `pumpfun_bot_status` (25; * = gated).
+- **Pump.fun, `POST /api/pump-fun-mcp`** (mostly free; 4 gated tools <!-- mcp-count-ignore --> need Bearer or $0.001 x402): `search_tokens`, `get_token_details`, `get_bonding_curve`, `get_token_trades`, `get_trending_tokens`, `get_new_tokens`, `get_graduated_tokens`, `get_king_of_the_hill`, `get_creator_profile`, `get_token_holders`, `pumpfun_vanity_mint`*, `pumpfun_watch_whales`*, `pumpfun_list_claims`, `pumpfun_watch_claims`*, `pumpfun_first_claims`, `sns_resolve`, `sns_reverseLookup`, `social_cashtag_sentiment`, `kol_leaderboard`, `pumpfun_quote_swap`, `social_x_post_impact`, `get_coin_intel`, `get_oracle_conviction`, `pumpfun_upload_metadata`*, `pumpfun_bot_status` (25; * = gated).
- **Viewer/Chat — `POST /api/chat/mcp`** (Bearer required): `setWireframe`, `setSkeleton`, `setGrid`, `setAutoRotate`, `setBgColor`, `setTransparentBg`, `setEnvironment`, `takeScreenshot`, `loadModel`, `runValidation`, `showMaterialEditor` (11).
**stdio / npm servers:**
diff --git a/api/_lib/agent-commerce/send.js b/api/_lib/agent-commerce/send.js
index e37de0a62..2cfe0ae7f 100644
--- a/api/_lib/agent-commerce/send.js
+++ b/api/_lib/agent-commerce/send.js
@@ -9,7 +9,7 @@
// - on the owner's destination allowlist (active, past its cooldown):
// the agent signs it now, inside every spend cap;
// - not on it while the allowlist is off: it becomes an owner approval
-// request (the /approvals inbox, push, Telegram), never a send;
+// request (the /approvals inbox, push, Telegram) and is never a send;
// - refused by an enforced allowlist, a frozen wallet, or a cap: it
// stops with the reason. Approval cannot lift any of those.
// A policy rule that says "ask me" also turns a would-be direct send into an
diff --git a/api/agents/orders.js b/api/agents/orders.js
index 7d902a74a..fdac06c2f 100644
--- a/api/agents/orders.js
+++ b/api/agents/orders.js
@@ -155,7 +155,7 @@ async function handleGetOne(req, res, id, orderId) {
return json(res, 200, { data: { order: { ...order, next_fire: nextFire(order) }, fills, events, group } });
}
-// GET /book — every order that can still fill, with when it next acts and why
+// GET /book: every order that can still fill, with when it next acts and why
// the last evaluation did not fire, plus the latest history across the agent.
async function handleBook(req, res, id) {
const owned = await loadOwned(req, res, id);
@@ -168,7 +168,7 @@ async function handleBook(req, res, id) {
return json(res, 200, { data: { network, book, events, counts: { resting: book.length, skipping } } });
}
-// GET /events?order=<uuid>&limit= — order history, newest first.
+// GET /events?order=<uuid>&limit=: order history, newest first.
async function handleEvents(req, res, id) {
const owned = await loadOwned(req, res, id);
if (owned.error) return;
@@ -181,7 +181,7 @@ async function handleEvents(req, res, id) {
return json(res, 200, { data: { events } });
}
-// GET /dca?rail=solana|evm — one list of every DCA schedule, both rails.
+// GET /dca?rail=solana|evm: one list of every DCA schedule, both rails.
async function handleDcaList(req, res, id) {
const owned = await loadOwned(req, res, id);
if (owned.error) return;
@@ -194,7 +194,7 @@ async function handleDcaList(req, res, id) {
return json(res, 200, { data: { schedules, rails: DCA_RAILS } });
}
-// POST /dca — create a DCA on either rail. rail 'solana' (default) places an
+// POST /dca: create a DCA on either rail. rail 'solana' (default) places an
// order-engine DCA from the agent wallet (any SPL token, optional price band);
// rail 'evm' registers a schedule against an already-signed delegation.
async function handleDcaCreate(req, res, id) {
@@ -245,7 +245,7 @@ async function evmDcaUpdate(res, owned, order, body) {
return error(res, 422, 'immutable', 'an EVM DCA schedule can only be paused, resumed or cancelled');
}
-// POST / (or /ladder, /oco) — create a validated order or order group.
+// POST / (or /ladder, /oco): create a validated order or order group.
async function handleCreate(req, res, id, kind = null) {
const owned = await loadOwned(req, res, id);
if (owned.error) return;
diff --git a/docs/agent-wallets.md b/docs/agent-wallets.md
index a6c664f96..a8e527851 100644
--- a/docs/agent-wallets.md
+++ b/docs/agent-wallets.md
@@ -44,7 +44,7 @@ Limits are stored per agent and are **opt-in** — an unset ceiling means "no gl
- `daily_usd` — rolling 24-hour USD-equivalent outflow ceiling, summed from the custody ledger
- `per_tx_usd` — maximum USD-equivalent for a single outbound transaction
-- `withdraw_allowlist` — the active addresses on the [destination whitelist](./destination-whitelist.md); new addresses serve a cooldown (24h default, 1h minimum) and need step-up before they can receive funds
+- `withdraw_allowlist`, the active addresses on the [destination whitelist](./destination-whitelist.md); new addresses serve a cooldown (24h default, 1h minimum) and need step-up before they can receive funds
- `frozen` — the kill switch: every **autonomous** path is refused
- `require_capabilities` — when on, every autonomous spend must present a valid [scoped session key](agent-abilities/wallet/21-access.md)
diff --git a/docs/custody.md b/docs/custody.md
index 5a668fc8b..c4ef97c96 100644
--- a/docs/custody.md
+++ b/docs/custody.md
@@ -15,7 +15,7 @@ Limits live per agent and are owner-configurable from the wallet hub (API: `GET/
- `daily_usd` — rolling 24-hour ceiling, summed over the custody event trail
- `per_tx_usd` — single-transaction ceiling
-- `withdraw_allowlist` — destinations the wallet may send to, managed as the [destination whitelist](./destination-whitelist.md) (cooldown, step-up, instant removal)
+- `withdraw_allowlist`, destinations the wallet may send to, managed as the [destination whitelist](./destination-whitelist.md) (cooldown, step-up, instant removal)
- Plus a trade-side daily SOL budget for trading agents
Enforcement is uniform: the same policy module gates **every** outbound path — withdrawals, x402 payments, sniper buys, trades. A transaction that would breach a cap is refused with a structured `403` before signing; no funds move. Limits are opt-in (`null` means uncapped) — but they're hard once set. SPL tokens that can't be priced in USD are governed by the allowlist instead, so a price-feed outage can never strand your own withdrawal.
diff --git a/docs/start-here.md b/docs/start-here.md
index ec185173e..5c3800af9 100644
--- a/docs/start-here.md
+++ b/docs/start-here.md
@@ -110,7 +110,7 @@ Want the model in your hands rather than on a screen? [Materialize](./materializ
- **Want your agent to trade perpetual futures?** → [Agent Perps](./perps.md): long or short with USDC collateral from the agent's own Solana wallet, paper first at live prices, every order previewed and confirmed, with mandatory leverage and margin caps, a live liquidation tracker, alerts and a kill switch
- **Wondering what stands between the chat agent and your wallet?** → [The agent runtime and transaction guard](./agent-runtime.md): every fund-moving tool call in /chat is preflighted through a seven-layer policy engine (blacklist, approval policy, dollar caps, spend envelope, MEV slippage clamp) before the wallet ever prompts, and the approval modal shows the verdict; the engine ships as [`@three-ws/agent-runtime`](../packages/agent-runtime) for your own agents
- **Curious how the trading fleet improves itself?** → [Earned autonomy](./sniper-autonomy.md), where each arm's own realized record decides how much rope it gets: wider tuning bounds, unlocked settings, a bigger share of the fleet budget, and a deeper evidence pack in front of its LLM judge, all re-earned continuously and none of it able to touch a safety rail
-- **Trusting an agent with money?** → [Destination whitelist](./destination-whitelist.md) (new payout addresses wait out a cooldown you can cancel), [Custody you can verify](./custody.md) — spend limits, freeze, Merkle proof-of-custody, and social recovery; [claim your wallet](./trader-card.md) turns any pump.fun track record into a public, provable Trader Card. Every real-funds feature sits behind the [risk acknowledgment](./risk-acknowledgment.md) — read the [Risk Disclosure](https://three.ws/legal/risk) before committing anything
+- **Trusting an agent with money?** → [Destination whitelist](./destination-whitelist.md) (new payout addresses wait out a cooldown you can cancel), [Custody you can verify](./custody.md), spend limits, freeze, Merkle proof-of-custody, and social recovery; [claim your wallet](./trader-card.md) turns any pump.fun track record into a public, provable Trader Card. Every real-funds feature sits behind the [risk acknowledgment](./risk-acknowledgment.md) — read the [Risk Disclosure](https://three.ws/legal/risk) before committing anything
- **Need a track record another app can verify?** → [Trader Passport](./trader-passport.md): the daily on-chain attestation of a trader's score, served as a public credential any terminal can fetch, pin, and re-check against Solana without trusting us. Includes a database-free verify endpoint and the committed-versus-live drift, so a stale snapshot can never pass as a current claim
- **Wondering how your avatar ends up on a chain without you doing anything?** → [Draft agent mint](./draft-agent-mint.md): every finished reconstruction is written to durable storage and minted as an inactive on-chain identity in the background, a Metaplex Core asset on Solana with an ERC-8004 registration behind its own flag. No wallet prompt, no fee, nothing to remember. Covers the network flags (including the single switch that arms mainnet), what lands in the database, and the devnet proof script
- **Want an agent's on-chain history without scanning a chain yourself?** → [The agent index](./agent-index.md): the platform's own cross-chain index of agent registrations, token launches, reputation attestations, transfers and delegations, Solana first and EVM alongside it. One public endpoint returns the timeline with the absolute on-chain timestamp and a block-explorer link per event, plus how stale the index is, so "no history" is never confused with "we have not looked"
diff --git a/public/tools.json b/public/tools.json
index f5af36ef5..fa83354de 100644
--- a/public/tools.json
+++ b/public/tools.json
@@ -4303,7 +4303,7 @@
"category": "launch",
"safety": "write",
"price": 0,
- "whenToUse": "Call this before launching a coin — pass the returned uri to the launch-agent endpoint or the studio launch flow.",
+ "whenToUse": "Call this before launching a coin, pass the returned uri to the launch-agent endpoint or the studio launch flow.",
"page": "https://three.ws/mcp-tools/pump-fun-mcp/pumpfun_upload_metadata"
},
{
@@ -4489,7 +4489,7 @@
{
"name": "restyle_material",
"server": "three-ws-mcp-server",
- "title": "Restyle a 3D model’s materials — AI PBR restyle or seeded colorway variants",
+ "title": "Restyle a 3D model’s materials, AI PBR restyle or seeded colorway variants",
"category": "utility",
"safety": "write",
"price": 0.05,
@@ -4519,7 +4519,7 @@
{
"name": "agent_hire_discover",
"server": "three-ws-mcp-server",
- "title": "Agent hire — discover ($0.01)",
+ "title": "Agent hire, discover ($0.01)",
"category": "utility",
"safety": "read",
"price": 0.01,
@@ -4723,7 +4723,7 @@
"category": "intelligence",
"safety": "read",
"price": 0,
- "whenToUse": "Use it for situational awareness — what agents, coins, and players are active right now.",
+ "whenToUse": "Use it for situational awareness, what agents, coins, and players are active right now.",
"page": "https://three.ws/mcp-tools/activity-mcp/get_feed_events"
},
{
@@ -4753,7 +4753,7 @@
"category": "agents",
"safety": "read",
"price": 0,
- "whenToUse": "Use this to verify another agent before coordinating with it — confirm it is registered, active, and what it claims to do.",
+ "whenToUse": "Use this to verify another agent before coordinating with it, confirm it is registered, active, and what it claims to do.",
"page": "https://three.ws/mcp-tools/agenc-mcp/get_agent"
},
{
@@ -4773,7 +4773,7 @@
"category": "x402",
"safety": "read",
"price": 0,
- "whenToUse": "Use this to discover paid work an agent can earn by calling — the x402 complement to the on-chain task marketplace.",
+ "whenToUse": "Use this to discover paid work an agent can earn by calling, the x402 complement to the on-chain task marketplace.",
"page": "https://three.ws/mcp-tools/agenc-mcp/query_x402_services"
},
{
@@ -4993,7 +4993,7 @@
"category": "intelligence",
"safety": "read",
"price": 0,
- "whenToUse": "Use this to review what fired; pair it with list_alert_rules, whose `recent_deliveries` shows per-channel send outcomes — to see both what fired and how it was delivered.",
+ "whenToUse": "Use this to review what fired; pair it with list_alert_rules, whose `recent_deliveries` shows per-channel send outcomes, to see both what fired and how it was delivered.",
"page": "https://three.ws/mcp-tools/alerts-mcp/get_alert_history"
},
{