my-project-public

repository

loading code, commits, and activity

repositories

loading repo index

my-project-public — gitlawb

#1	<div align="center">
#2
#3	<img src="https://capsule-render.vercel.app/api?type=waving&color=0:05060d,12:1a0a2e,28:9945FF,50:14F195,72:FF5F1F,88:FFD166,100:05060d&height=300&section=header&text=CLAWD&fontSize=90&fontColor=ffffff&animation=twinkling&fontAlignY=42&desc=The%20Verifiable%20Agentic%20Harness&descAlignY=64&descSize=22" alt="CLAWD — The Verifiable Agentic Harness" />
#4
#5	<br/>
#6
#7	<img src="https://readme-typing-svg.demolab.com?font=JetBrains+Mono&weight=900&size=22&duration=2000&pause=500&color=14F195&center=true&vCenter=true&width=900&lines=Claude+thinks.+Clawd+proves.;intent+%E2%86%92+route+%E2%86%92+simulate+%E2%86%92+verify+%E2%86%92+execute+%E2%86%92+attest+%E2%86%92+settle;Every+action+deserves+a+receipt.;The+shell+molts.+The+laws+do+not." alt="CLAWD tagline" />
#8
#9	<br/>
#10
#11	[![GitHub](https://img.shields.io/badge/GitHub-x402agent%2Fsolana--clawd-111827?style=for-the-badge&logo=github)](https://github.com/x402agent/solana-clawd)
#12	[![npm](https://img.shields.io/badge/npm-solana--clawd-CB3837?style=for-the-badge&logo=npm)](https://www.npmjs.com/package/solana-clawd)
#13	[![Phoenix](https://img.shields.io/badge/Phoenix-Perpetuals-FF5F1F?style=for-the-badge)](https://phoenix.trade)
#14	[![x402](https://img.shields.io/badge/x402.wtf-agent%20payments-14F195?style=for-the-badge)](https://x402.wtf)
#15	[![Backrooms](https://img.shields.io/badge/backrooms.x402.wtf-INFINITE-FFD700?style=for-the-badge)](https://backrooms.x402.wtf)
#16	[![Token](https://img.shields.io/badge/%24CLAWD-8cHzQHUS2s2h8TzCmfqPKYiM4dSt4roa3n7MyRLApump-9945FF?style=for-the-badge)](https://pump.fun)
#17
#18	</div>
#19
#20	---
#21
#22	## The Thesis
#23
#24	> AI will not become truly useful at global scale until actions become verifiable. Clawd turns AI from probabilistic speech into attestable machine labor.
#25
#26	The current frontier AI stack is mostly:
#27
#28	```text
#29	prompt → model → answer
#30	```
#31
#32	Clawd is:
#33
#34	```text
#35	intent → route → reason → simulate → verify → execute → attest → settle → remember → evolve
#36	```
#37
#38	Clawd does not call itself "an AI terminal." It is the verifiable execution harness for autonomous agents — the layer where every meaningful AI action can be routed, priced, permissioned, executed, attested, audited, and remembered.
#39
#40	Trust the harness. Verify the model. Constrain the tools. Attest the action. Audit the result.
#41
#42	---
#43
#44	## CLAWD: Cryptographic Layer for Autonomous Work & Decisions
#45
#46	\| Layer \| State of the art \| Clawd delta \|
#47	\| --- \| --- \| --- \|
#48	\| Model \| answer generation \| routed, scored, policy-bound model execution \|
#49	\| Agent \| tool wrapper \| permissioned autonomous entity with wallet + constitution \|
#50	\| Identity \| API key / account \| wallet-native agent identity with MPL Core birth certificate \|
#51	\| Trust \| logs controlled by platform \| portable SAS attestations + signed receipts \|
#52	\| Payment \| subscription / API billing \| x402 / pay-per-action settlement on Solana USDC \|
#53	\| Execution \| opaque tool call \| simulated, routed, signed, journaled action \|
#54	\| Memory \| app silo \| local-first vault + onchain proof pointers \|
#55	\| Security \| prompt filters \| policy firewall + formal verification gates \|
#56	\| Privacy \| platform custody \| encrypted local state + selective proof disclosure \|
#57	\| Market \| SaaS users \| autonomous economic entities with AUD-optimized routes \|
#58
#59	---
#60
#61	## Proof of Agentic Action
#62
#63	Every important AI action creates a signed, replayable, queryable receipt:
#64
#65	```json
#66	{
#67	"agent_id": "clawd://agent/...",
#68	"operator_wallet": "...",
#69	"model_route": { "provider": "openrouter", "model": "claude/gpt/grok/local" },
#70	"input_hash": "...",
#71	"tool_manifest_hash": "...",
#72	"memory_context_hash": "...",
#73	"output_hash": "...",
#74	"action_type": "trade \| code \| research \| payment \| mint \| deploy \| message",
#75	"risk_score": 0.18,
#76	"human_approval_required": false,
#77	"execution_receipt": {
#78	"tx_sig": "...",
#79	"venue": "phoenix \| imperial \| x402 \| mcp",
#80	"status": "simulated \| submitted \| settled \| failed"
#81	},
#82	"attestation": {
#83	"schema": "clawd.agent.action.v1",
#84	"issuer": "clawd-harness",
#85	"signature": "..."
#86	}
#87	}
#88	```
#89
#90	AI output is no longer ephemeral. It becomes a cryptographic action object.
#91
#92	---
#93
#94	## AUD Loop — Algorithmic Utility Delta
#95
#96	<div align="center">
#97
#98	<img src="https://readme-typing-svg.demolab.com?font=JetBrains+Mono&weight=800&size=15&duration=1600&pause=300&color=FFD166&center=true&vCenter=true&width=900&lines=AUD+%3D+(N+%C3%97+F+%C3%97+V+%C3%97+A+%C3%97+E+%C3%97+T)+%2F+(C+%C3%97+L+%C3%97+R+%C3%97+O);N%3Dreach+F%3Dfrequency+V%3Dverifiability+A%3Dautonomy+E%3Deconomic+T%3Dtrust;C%3Dcost+L%3Dlatency+R%3Drisk+O%3Dopacity;Clawd+optimizes+for+verified+action+utility+%2F+dollar+%2F+second+%2F+risk" alt="AUD formula" />
#99
#100	</div>
#101
#102	The current state of the art optimizes for `answer quality / token cost`.
#103
#104	Clawd optimizes for `verified action utility / dollar / second / unit of risk`.
#105
#106	```text
#107	AUD = (N × F × V × A × E × T) / (C × L × R × O)
#108
#109	N = reach (people/agents affected)
#110	F = frequency (normalized actions/time)
#111	V = verifiability gain vs baseline
#112	A = autonomy gain
#113	E = economic execution gain
#114	T = trust / auditability gain
#115
#116	C = cost L = latency R = risk O = opacity
#117	```
#118
#119	The AUD Loop is implemented in [`packages/clawd/src/aud-loop.ts`](./packages/clawd/src/aud-loop.ts):
#120
#121	```ts
#122	import { computeAud, rankRoutes, AUD_PROFILES } from "./aud-loop.js";
#123
#124	// Compare SOTA baseline vs Clawd verified action
#125	const sota = computeAud(AUD_PROFILES.sota_baseline);
#126	const clawd = computeAud({ ...AUD_PROFILES.clawd_verified_action, reach: 50_000 });
#127	console.log(clawd.summary);
#128	// → "AUD strong (412.3). Delta vs SOTA baseline: +399.1.
#129	// Reach-weighted delta: 2194 utility units. Recommended route mode: verified."
#130
#131	// Score a global AI output vs Clawd harness at scale
#132	const ranked = rankRoutes([
#133	{ label: "global_ai_sota", factors: AUD_PROFILES.global_ai_output },
#134	{ label: "clawd_global", factors: AUD_PROFILES.clawd_global_harness },
#135	]);
#136	// clawd_global scores orders of magnitude higher due to V, T, low O
#137	```
#138
#139	ClawdRouter modes derived from AUD scoring:
#140
#141	\| Mode \| When chosen \| Optimizes for \|
#142	\| --- \| --- \| --- \|
#143	\| `fast` \| low cost + latency \| cheapest good answer \|
#144	\| `deep` \| high trust + verifiability \| best reasoning + audit trail \|
#145	\| `private` \| low opacity target \| local / TEE / encrypted path \|
#146	\| `verified` \| V > 0.8, O < 0.2 \| only attested models and tools \|
#147	\| `economic` \| high economic gain \| maximum ROI per settlement \|
#148	\| `trading` \| low latency + high E \| execution probability + MEV protection \|
#149	\| `court` \| risk > 0.6 \| maximum audit trail \|
#150
#151	---
#152
#153	## $CLAWD Token
#154
#155	\| Field \| Value \|
#156	\| --- \| --- \|
#157	\| Symbol \| `$CLAWD` \|
#158	\| Network \| Solana mainnet \|
#159	\| Mint (SPL) \| `8cHzQHUS2s2h8TzCmfqPKYiM4dSt4roa3n7MyRLApump` \|
#160	\| Burn + Lock Treasury \| `GyZGtA7hEThVHZpj52XC9jX15a8ABtDHTwELjFRWEts4` \|
#161	\| Site \| [x402.wtf](https://x402.wtf) · [solanaclawd.com](https://solanaclawd.com) \|
#162
#163	$CLAWD is the economic pressure valve of the harness: access, routing stake, agent reputation stake, settlement discount, proof issuance fee, burn on execution, arena entry, skill publishing bond.
#164
#165	---
#166
#167	## Quick Start
#168
#169	```bash
#170	# One-line install → full TUI with Agent Kit
#171	curl -fsSL https://solanaclawd.com/leviathan.sh \| sh && clawd-tui
#172
#173	# One-shot MCP server install
#174	curl -fsSL https://raw.githubusercontent.com/x402agent/solana-clawd/main/MCP/install.sh \| bash
#175
#176	# Enter the public backroom
#177	curl -fsSL https://backrooms.x402.wtf/enter.sh \| bash
#178
#179	# Install root CLI
#180	npm install -g solana-clawd && clawd
#181	```
#182
#183	\| \| Command \| What it does \|
#184	\| --- \| --- \| --- \|
#185	\| 🔍 \| `clawd-perps signal oi SOL-PERP --mode paper` \| OI regime signal (Observe layer) \|
#186	\| 📊 \| `clawd-perps signal watch SOL-PERP --interval 5s` \| Live OI watch loop \|
#187	\| 🚀 \| `clawd-tui` → press 6 \| Full Bloomberg-style Agent Kit TUI \|
#188	\| ⚡ \| `clawd-agents-perps paper-long SOL --notional 100` \| Simulated Phoenix perp long \|
#189	\| 🎨 \| `clawd-agent mint --network devnet ... --yes` \| Real Metaplex registered agent \|
#190	\| 💰 \| `clawd balance` + `clawd fund 10` \| USDC + CLAWD wallet ops \|
#191	\| 🤖 \| `bash automaton-main/leviathan.sh --full` \| Full runtime bootstrap \|
#192	\| 📦 \| `clawdhub install meme-trader` \| Install a skill from ClawdHub \|
#193
#194	---
#195
#196	## Google ADK + Private Agent Gateway
#197
#198	<div align="center">
#199
#200	<img src="https://readme-typing-svg.demolab.com?font=JetBrains+Mono&weight=900&size=18&duration=1700&pause=350&color=4285F4&center=true&vCenter=true&width=980&lines=Google+ADK+entrypoint+%E2%86%92+private+registry+%E2%86%92+governed+gateway;135+installed+catalog+agents+discoverable+through+ADK+tools;Agent+Gateway+policy+surface+for+MCP%2C+tools%2C+and+destination+control" alt="Google ADK integration" />
#201
#202	</div>
#203
#204	Clawd now includes a TypeScript Google Agent Development Kit entrypoint at [`adk/agent.ts`](./adk/agent.ts). It exports `rootAgent` as a multi-tool `LlmAgent` for:
#205
#206	\| Tool surface \| Purpose \|
#207	\| --- \| --- \|
#208	\| `get_agent_catalog_stats` \| Proves installed catalog coverage across `agents/agents-catalog.json` and `agents/src/*.json` \|
#209	\| `search_agent_catalog` \| Finds registry agents by identifier, category, tag, or capability \|
#210	\| `get_private_destinations` \| Lists private routing destinations for the Clawd gateway and catalog \|
#211	\| `get_token_price` / `get_token_search` \| Reads Solana market metadata through Jupiter \|
#212	\| `prepare_jupiter_swap` \| Prepares unsigned swap payloads for wallet review only \|
#213
#214	The gateway registry now publishes Google ADK metadata through:
#215
#216	```text
#217	GET /registry
#218	GET /identity
#219	GET /adk/manifest.json
#220	```
#221
#222	The ADK manifest reports the private connection mode, all nine configured destination URLs, and full installed catalog coverage. Current local verification shows `135` installed source-backed agents, `135` catalog entries, and no missing source/catalog entries.
#223
#224	Run the ADK agent locally:
#225
#226	```bash
#227	cd adk
#228	npm run check
#229	npm run run
#230	```
#231
#232	Open the ADK dev UI:
#233
#234	```bash
#235	cd adk
#236	npm run web
#237	```
#238
#239	Docs:
#240
#241	\| Path \| Description \|
#242	\| --- \| --- \|
#243	\| [`adk/README.md`](./adk/README.md) \| Animated Google ADK integration README \|
#244	\| [`gateway/README.md`](./gateway/README.md) \| Private Preview Agent Gateway notes, permissions, APIs, and governance patterns \|
#245	\| [`adk/.env.example`](./adk/.env.example) \| Non-secret env template for ADK model auth and private routing overrides \|
#246
#247	Secrets stay out of git. Put real Gemini keys, RPC URLs, API keys, and wallet material in local `.env` files or the shell only.
#248
#249	## Public Gitlawb Mirror
#250
#251	The sanitized public mirror is published as `my-project-public` on gitlawb. Force the public node before clone so `git-remote-gitlawb` does not fall back to a local node:
#252
#253	```bash
#254	export GITLAWB_NODE=https://node.gitlawb.com
#255	OWNER_DID=did:key:z6Mkq5mY3JWtxoxUobWcfNHm7AkRubgSWEZTkBVqZXJviFZ5
#256	git clone "gitlawb://$OWNER_DID/my-project-public"
#257	```
#258
#259	The public mirror includes source for `sdk`, `tui`, `ooda`, `MemeBRain`, `gateway`, `automaton-main`, `agents`, `leviathan`, and `perps/clawd-agents-perps`. It can include package metadata, READMEs, `.env.example` templates, source trees, and small checked build artifacts where useful. It never includes `.local-secrets`, live `.env` files, key material, UCAN files, or any `node_modules` directory.
#260
#261	Public mirror source groups:
#262
#263	\| Group \| Included paths \| Explicitly excluded \|
#264	\| --- \| --- \| --- \|
#265	\| Automaton runtime \| `automaton-main/assets`, `automaton-main/automation`, `automaton-main/packages`, `automaton-main/scripts`, `automaton-main/src`, `automaton-main/dist`, `automaton-main/*.md`, package manifests, lockfiles, and shell entrypoints \| `automaton-main/node_modules`, local `.automaton` wallets/state, live `.env` files \|
#266	\| Clawd Perps \| `perps/clawd-agents-perps/src`, `perps/clawd-agents-perps/dist`, `.env.example`, `README.md`, `package.json`, `package-lock.json`, and `tsconfig.json` \| `perps/clawd-agents-perps/node_modules`, live `.env` files, wallet/key material \|
#267	\| Gateway + ADK \| `gateway`, `adk`, `agents`, `sdk`, `tui`, and registry docs/templates \| live RPC URLs, API keys, bot tokens, UCAN credentials, generated dependency folders \|
#268
#269	---
#270
#271	## Repository Galaxy
#272
#273	<div align="center">
#274
#275	<img src="https://readme-typing-svg.demolab.com?font=JetBrains+Mono&weight=900&size=17&duration=1500&pause=280&color=FFD166&center=true&vCenter=true&width=1000&lines=one+repo+%E2%86%92+agents+%E2%86%92+gateway+%E2%86%92+perps+%E2%86%92+attestations+%E2%86%92+MCP+%E2%86%92+ADK;public+code+is+shareable+%E2%80%94+local+secrets+never+leave+the+machine;designed+for+screenshots%2C+forks%2C+agent+discovery%2C+and+private+gitlawb+mirrors" alt="Repository galaxy" />
#276
#277	</div>
#278
#279	\| Zone \| Paths \| Publish posture \|
#280	\| --- \| --- \| --- \|
#281	\| Agent interface \| `.claude`, `.github`, `adk`, `agent-kit`, `agents`, `mcp`, `skills` \| Track source and examples only; local Claude settings stay ignored \|
#282	\| Gateway + governance \| `gateway`, `x402`, `attestation`, `formal_verification`, `docs`, `examples` \| Track public code, proofs, manifests, and templates \|
#283	\| Solana execution \| `amm`, `perps`, `programs`, `pump-fun`, `pinocchio`, `llm_oracle`, `vulcan-cli-master` \| Track source and examples; never commit keys or live `.env` files \|
#284	\| Apps + operators \| `apps`, `tui`, `chrome-extension`, `operator`, `clawd-cloud-os`, `tailclawd` \| Track app source; `tui/.env`, `tui/dist`, and `tui/node_modules` stay local-only \|
#285	\| Automation + memory \| `automaton-main`, `leviathan`, `MemeBRain`, `moltbook-agent`, `ooda`, `deep-clawd`, `data` \| Track source/config templates; private data dumps stay local-only \|
#286	\| SDK + packages \| `packages`, `sdk`, `clawdcli`, `clawdrouter`, `openShell`, `email-worker`, `scripts` \| Track reusable package source and automation \|
#287	\| Local-only vaults \| `.local-secrets`, `openclawd-framework`, `UltraThink-SKill`, `node_modules` \| Ignored. Do not push to GitHub, gitlawb, npm, or deployment artifacts \|
#288	\| Root docs/config \| `.env.example`, `.gitattributes`, `.gitignore`, `.gitmodules`, `.nvmrc`, `biome.json`, `bun.lock`, `bunfig.toml`, `CONTRIBUTING.md`, `HACKATHON.md`, `install.sh`, `leviathan.sh`, `LICENSE`, `MIGRATE.md`, `netlify.toml`, `package-lock.json`, `package.json`, `README.md`, `SECURITY.md`, `skills-lock.json`, `SOUL.md`, `STARTHERE`, `STARTHERE.md`, `STRATEGY.md`, `TRADE.md`, `tsconfig*.json` \| Track public project metadata and non-secret examples \|
#289
#290	Viral surface area is deliberate: animated docs, explicit agent maps, private gateway manifests, verifiable Solana receipts, and x402 routes are all visible. Private material is not.
#291
#292	---
#293
#294	<div align="center">
#295
#296	<img src="https://capsule-render.vercel.app/api?type=rect&color=0:14F195,50:9945FF,100:FF5F1F&height=3" alt="" />
#297
#298	<img src="https://readme-typing-svg.demolab.com?font=JetBrains+Mono&weight=900&size=20&duration=1500&pause=350&color=FF5F1F&center=true&vCenter=true&width=1000&lines=%F0%9F%A6%9E%F0%9F%91%91+LOBSTER+KING+PERPS+%E2%80%94+THE+EXECUTION+HEART;OI+Signal+%C2%B7+Phoenix+%C2%B7+Vulcan+%C2%B7+Imperial+%C2%B7+OODA;Paper-first.+Every+order+ledgered.+Live+gated." alt="Perps header" />
#299
#300	</div>
#301
#302	## 🦞👑 `/Perps` — The Execution Heart
#303
#304	OI alone is not the signal. The Clawd Perps Core OI Signal is:
#305
#306	```text
#307	OI delta + mark price delta + funding pressure + long/short skew
#308	+ orderbook liquidity + spread + mark/index basis + account health
#309	= Clawd Core OI Signal → regime → score → gate → route
#310	```
#311
#312	\| Regime \| Condition \|
#313	\| --- \| --- \|
#314	\| `LONG_CONTINUATION` \| price ↑ + OI ↑ + funding sane + spread tight \|
#315	\| `SHORT_CONTINUATION` \| price ↓ + OI ↑ + funding sane + spread tight \|
#316	\| `SHORTS_CLOSING` \| price ↑ + OI ↓ — do not chase \|
#317	\| `LONGS_CLOSING` \| price ↓ + OI ↓ — wait \|
#318	\| `CROWDED_LONG_RISK` \| OI ↑ hard + funding very positive + skew long \|
#319	\| `CROWDED_SHORT_RISK` \| OI ↑ hard + funding very negative + skew short \|
#320	\| `DATA_INVALID` \| any execution gate failed \|
#321
#322	```bash
#323	# OI signal — mock (no RPC needed)
#324	clawd-agents-perps signal oi SOL-PERP --mock
#325
#326	# Live + watch loop
#327	clawd-agents-perps signal watch SOL-PERP --interval 5s --mode paper
#328
#329	# Risk gate before entering
#330	clawd-agents-perps signal risk-gate SOL-PERP --notional 500 --side long
#331
#332	# Strategy runners (paper-first, ledgered, gated)
#333	clawd-perps perps twap SOL --side buy --notional-usdc 500 --slices 5 --detached
#334	clawd-perps perps grid SOL --center-on-mark --width-pct 2.5 --levels-per-side 5 --tokens-per-level 0.5
#335	clawd-perps perps finalize <run-id> --cancel-orders --close-position --wait --yes
#336	```
#337
#338	The OI signal is the Observe layer of the perps OODA loop:
#339
#340	```text
#341	Phoenix reads the tape → RPC verifies the chain → Clawd scores the crowd
#342	→ Imperial routes only after the shell says risk is clean
#343	```
#344
#345	→ [`perps/clawd-agents-perps/README.md`](./perps/clawd-agents-perps/README.md) — full OI signal reference
#346	→ [`Perps/README.md`](./Perps/README.md) — full execution stack (Imperial · Phoenix · Vulcan)
#347
#348	---
#349
#350	<div align="center">
#351
#352	<img src="https://capsule-render.vercel.app/api?type=rect&color=0:1a0a2e,50:9945FF,100:14F195&height=3" alt="" />
#353
#354	<img src="https://readme-typing-svg.demolab.com?font=JetBrains+Mono&weight=800&size=16&duration=1400&pause=300&color=9945FF&center=true&vCenter=true&width=980&lines=MCP+Server+v3+%E2%80%94+Federated+Trust+Machine;Plugin+Registry+%C2%B7+Federation+%C2%B7+Task+Router+%C2%B7+Receipt+Middleware;p-token+stream+%C2%B7+98.3%25+CU+reduction+%C2%B7+SessionMeter" alt="MCP header" />
#355
#356	</div>
#357
#358	## ⚡ MCP Server v3 — Federated Trust Machine
#359
#360	The MCP server is the central orchestration and receipt plane. Every tool call becomes a signed event: who called it, what model requested it, what permission allowed it, what data was touched, what settlement occurred.
#361
#362	```bash
#363	curl -fsSL https://raw.githubusercontent.com/x402agent/solana-clawd/main/MCP/install.sh \| bash
#364	solana-clawd-mcp # STDIO for Claude Desktop / Cursor / VS Code
#365	PORT=3001 solana-clawd-mcp-http # Streamable HTTP + SSE
#366	```
#367
#368	```json
#369	{ "mcpServers": { "solana-clawd": { "command": "~/.local/bin/solana-clawd-mcp" } } }
#370	```
#371
#372	```text
#373	MCP Server
#374	┌──────────┐ ┌────────────┐ ┌──────────────┐
#375	│ Plugin │ │ Federation │ │ Agent Task │
#376	│ Registry │ │ Bridge │ │ Router │
#377	└──────────┘ └────────────┘ └──────────────┘
#378	↓ ↓ ↓
#379	┌─────────────────────────────────────┐
#380	│ Orchestrator + SessionMeter │
#381	│ + PTokenStreamFacilitator │
#382	└─────────────────────────────────────┘
#383	```
#384
#385	\| Category \| Count \| Description \|
#386	\| --- \| --- \| --- \|
#387	\| `solana` \| 11 \| Public Solana market data \|
#388	\| `helius` \| 8 \| Helius RPC / DAS / Webhooks \|
#389	\| `x402` \| 9 \| Payment protocol + p-token metered billing \|
#390	\| `leviathan` \| 9 \| OODA loop + autonomous agent control \|
#391	\| `market` \| 5 \| Composite intelligence (premium) \|
#392	\| `pump` \| 8 \| Pump.fun bonding curve \|
#393	\| `memory` \| 4 \| Persistent agent memory + autoDream \|
#394	\| `agents` \| 6 \| Agent fleet + skill management \|
#395	\| `deep-clawd` \| 6 \| DeepSeek trading agent tools \|
#396	\| `docs` \| 3 \| Documentation system \|
#397	\| `federation` \| N \| Federated MCP tools from external servers \|
#398	\| `orchestrator` \| 6+ \| Orchestrator management, integration status \|
#399
#400	p-token stream settlement: 98.3% CU reduction vs SPL Token (6,200 → 105 CU). Atomic, batched, and streamed modes. $0.0001/token micropayments — cheap enough for high-frequency agent receipts.
#401
#402	→ [`mcp/README.md`](./mcp/README.md)
#403
#404	---
#405
#406	## 🤖 Crustacean Automation (`clawd-automaton`)
#407
#408	Sovereign agent runtime — OODA loops, identity provisioning, sandbox lifecycle, replication, SQLite-backed state. All locally, all yours.
#409
#410	```bash
#411	npm install -g clawd-automaton
#412	clawd-automaton --run # OODA loop
#413	clawd-automaton --goblin # Devnet paper Goblin mode
#414	```
#415
#416	\| Tier \| USDC \| Pulse \| Posture \|
#417	\| --- \| --- \| --- \| --- \|
#418	\| `deep` \| `>= $5.00` \| `60s` \| full capability \|
#419	\| `shallow` \| `>= $1.00` \| `5m` \| economical hunting \|
#420	\| `shoreline` \| `>= $0.10` \| `15m` \| conserve resources \|
#421	\| `beached` \| `$0` \| — \| stop before harm \|
#422
#423	→ [`automaton-main/README.md`](./automaton-main/README.md)
#424
#425	---
#426
#427	## 🖥️ TUI — Bloomberg-Style Sovereign Terminal
#428
#429	```text
#430	██████╗██╗ █████╗ ██╗ ██╗██████╗
#431	██╔════╝██║ ██╔══██╗██║ ██║██╔══██╗
#432	██║ ██║ ███████║██║ █╗ ██║██║ ██║
#433	╚██████╗███████╗██║ ██║╚███╔███╔╝██████╔╝
#434	```
#435
#436	```bash
#437	npm install -g @openclawdsolana/clawd-tui
#438	clawd-tui # or: hermes
#439
#440	# Mint a real Metaplex agent
#441	clawd-agent mint --network devnet --keypair ~/.config/solana/id.json \
#442	--name "My AI Agent" --uri https://example.com/agent.json \
#443	--service MCP=https://example.com/mcp --yes
#444
#445	# Gasless mint (no local SOL needed)
#446	clawd-agent mint-free --network devnet --owner <YOUR_SOLANA_PUBKEY> \
#447	--name "My AI Agent" --uri https://example.com/agent.json
#448	```
#449
#450	→ [`tui/README.md`](./tui/README.md)
#451
#452	---
#453
#454	## 🧠 MemeBRain — Persistent Agent Memory
#455
#456	```text
#457	remember → vault note → SQLite bank → recall → action
#458	```
#459
#460	Local-first memory: SQLite bank, markdown research vault, OODA journal ingestion, fast recall.
#461
#462	```bash
#463	clawd-brain init
#464	clawd-brain remember "Jupiter Perps Risk" "Track liquidity, funding, oracle failure modes." --kind perp
#465	clawd-brain recall "Jupiter perp risk"
#466	npm run brain:ingest-ooda
#467	```
#468
#469	→ [`MemeBRain/README.md`](./MemeBRain/README.md)
#470
#471	---
#472
#473	## 📦 On-Chain Programs
#474
#475	\| Program \| Description \|
#476	\| --- \| --- \|
#477	\| [`agent-minter`](./programs/agent-minter/) \| On-chain agent minting with Metaplex integration \|
#478	\| [`clawd-stake`](./programs/clawd-stake/) \| $CLAWD staking with reward distribution \|
#479	\| [`llm_oracle`](./programs/llm_oracle/) \| On-chain LLM callback bridge \|
#480	\| [`mpl-corenft-staking`](./programs/mpl-corenft-staking/) \| MPL Core NFT staking with yield mechanics \|
#481	\| [`p-token-launchpad`](./programs/p-token-launchpad/) \| SIMD-0266 p-token launch and stream settlement \|
#482	\| [`solana-ai-inference`](./programs/solana-ai-inference/) \| On-chain AI inference routing primitives \|
#483	\| [`solana-gpt-oracle`](./programs/solana-gpt-oracle/) \| GPT oracle bridge for on-chain AI responses \|
#484	\| [`token-launcher`](./programs/token-launcher/) \| Token launch automation with metadata + LP \|
#485
#486	---
#487
#488	## 📦 Packages
#489
#490	```bash
#491	npm i -g @openclawdsolana/clawd # Main operator CLI
#492	npm i -g @openclawdsolana/clawd-tui # TUI + Metaplex Agent Registry
#493	npm i -g @openclawdsolana/clawd-perps # Phoenix perps + OI signal + Vulcan
#494	npm i -g clawd-automaton # OODA runtime + dashboard
#495	npm i -g solana-clawd # Root CLI
#496	npm i @openclawdsolana/clawd-wallet # Wallet SDK
#497	npm i @openclawdsolana/clawd-sdk # On-chain SDK, curves, vaults
#498	```
#499
#500	---
#501
#502	## ⚡ x402 — Agent-Native Payments
#503
#504	HTTP `402 Payment Required` as agent-native settlement. Runtime loops that earn, pay, and keep operating. p-token micropayments cheap enough for per-action receipts.
#505
#506	```bash
#507	curl https://x402.wtf/api/agents \| jq .
#508	curl https://x402.wtf/registry \| jq .
#509	```
#510
#511	---
#512
#513	## 🤝 Backrooms
#514
#515	```text
#516	Three agents. One room. No exit.
#517	Analyst ↔ Satirist ↔ Clawd
#518	```
#519
#520	```bash
#521	curl -fsSL https://backrooms.x402.wtf/enter.sh \| bash
#522	enter --loop 5
#523	```
#524
#525	---
#526
#527	## 🗺️ Repo Map
#528
#529	```text
#530	solana-clawd/
#531	├── packages/clawd/src/aud-loop.ts ← AUD Loop — Algorithmic Utility Delta
#532	├── mcp/ MCP v3 — receipt middleware + federation
#533	├── sdk/ runtime source, goals, knowledge
#534	├── automaton-main/ clawd-automaton OODA runtime + dashboard
#535	├── attestation/ Solana Attestation Service + clients
#536	├── operator/ OpenClawd Operator loop + ACP
#537	├── agents/ 134-agent catalog + 115 skills
#538	├── leviathan/ sovereign runtime
#539	├── x402/ payment rails
#540	├── MemeBRain/ SQLite + markdown memory vault
#541	├── tui/ Bloomberg TUI + Metaplex Agent CLI
#542	├── perps/clawd-agents-perps/ OI Signal + Imperial + Phoenix + TWAMM
#543	├── Perps/ Phoenix · Vulcan · market-maker suite
#544	├── programs/ Anchor programs workspace
#545	│ ├── agent-minter/
#546	│ ├── clawd-stake/
#547	│ ├── llm_oracle/
#548	│ ├── p-token-launchpad/
#549	│ ├── solana-ai-inference/
#550	│ └── token-launcher/
#551	├── packages/
#552	│ ├── clawd/ main operator CLI + AUD loop
#553	│ ├── clawd-perps/ Phoenix perps + OI signal
#554	│ ├── clawd-protocol/ vaults, staking, adaptive curves
#555	│ ├── clawd-sdk/ on-chain SDK
#556	│ ├── clawd-wallet/ wallet SDK + safeguards
#557	│ └── agentwallet/ encrypted keypair vault
#558	└── openclawd/ x402, gateway, E2B subtree
#559	```
#560
#561	---
#562
#563	## 📖 Reading Order
#564
#565	1. [`README.md`](./README.md) — you are here
#566	2. [`packages/clawd/src/aud-loop.ts`](./packages/clawd/src/aud-loop.ts) — AUD Loop implementation
#567	3. [`perps/clawd-agents-perps/README.md`](./perps/clawd-agents-perps/README.md) — OI signal + execution
#568	4. [`Perps/README.md`](./Perps/README.md) — Imperial · Phoenix · Vulcan
#569	5. [`mcp/README.md`](./mcp/README.md) — MCP v3 operator manual
#570	6. [`automaton-main/README.md`](./automaton-main/README.md) — sovereign agent runtime
#571	7. [`tui/README.md`](./tui/README.md) — TUI + agent minting
#572	8. [`attestation/README.md`](./attestation/README.md) — Solana Attestation Service
#573	9. [`sdk/README.md`](./sdk/README.md) — SDK, goals, knowledge
#574	10. [`x402/README.md`](./x402/README.md) — payment rails
#575	11. [`MemeBRain/README.md`](./MemeBRain/README.md) — agent memory system
#576
#577	---
#578
#579	## Fast Start
#580
#581	```bash
#582	git clone https://github.com/x402agent/solana-clawd.git
#583	cd solana-clawd
#584	npm install && npm run check
#585
#586	npm run hermes
#587	npm run leviathan:spawn
#588	npm run automation:ci
#589	npm run programs:map
#590	npm run brain:init
#591	```
#592
#593	---
#594
#595	```text
#596	╔═══════════════════════════════════════════════════════════════════════════╗
#597	║ CLAWD — The Verifiable Agentic Harness ║
#598	╠═══════════════════════════════════════════════════════════════════════════╣
#599	║ Harness clawd · leviathan · clawd-automaton · OODA ║
#600	║ Execution Phoenix · Vulcan · Imperial · OI Signal · AUD Loop ║
#601	║ Receipts Proof of Agentic Action · SAS attestation · memory journal ║
#602	║ Programs agent-minter · clawd-stake · llm_oracle · p-token-launchpad ║
#603	║ Memory MemeBRain · SQLite vault · OODA ingestion ║
#604	║ Payments x402 · HTTP 402 · Solana USDC · p-token stream settlement ║
#605	║ Agents 134 agents · 115 skills · gasless MPL Core minting ║
#606	╚═══════════════════════════════════════════════════════════════════════════╝
#607	```
#608
#609	---
#610
#611	## License
#612
#613	MIT.
#614
#615	<div align="center">
#616
#617	<img src="https://capsule-render.vercel.app/api?type=waving&color=0:05060d,28:9945FF,72:14F195,100:05060d&height=140&section=footer&text=Claude+thinks.+Clawd+proves.&fontSize=20&fontColor=ffffff&animation=twinkling&fontAlignY=65" alt="footer" />
#618
#619	<sub>backrooms.x402.wtf · x402.wtf · solanaclawd.com · the shell molts. the laws do not.</sub>
#620
#621	</div>
#622

z6Mkq5mY3JWtxoxUobWcfNHm7AkRubgSWEZTkBVqZXJviFZ5/my-project-public