profbernardoj/NanoClaw/.claude/skills/add-morpheus
NanoClaw/.claude/skills/add-morpheus/SKILL.md
# Add [REDACTED] — Decentralized Inference for NanoClaw ## What This Does Connects NanoClaw to the EverClaw proxy for decentralized AI inference via the [REDACTED] network. The proxy runs on the host machine and is reachable from Docker containers. ## When To Use Use `/add-morpheus` to: - Enable hybrid mode (Claude orchestration + [REDACTED] inference) - Check proxy health - Switch default inference model ## Setup The EverClaw proxy must be running on the host (installed via `setup.sh`).
$ install --global
skillsauthnpx skillsauth add profbernardoj/everclaw-community-branches NanoClaw/.claude/skills/add-morpheusInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 15, 2026, 8:01 AM87.0s1 file scanned
SKILL.md
Add [REDACTED] — Decentralized Inference for NanoClaw
What This Does
Connects NanoClaw to the EverClaw proxy for decentralized AI inference via the [REDACTED] network. The proxy runs on the host machine and is reachable from Docker containers.
When To Use
Use /add-morpheus to:
- Enable hybrid mode (Claude orchestration + [REDACTED] inference)
- Check proxy health
- Switch default inference model
Setup
The EverClaw proxy must be running on the host (installed via setup.sh).
Environment Variables
Add to the NanoClaw container environment:
MORPHEUS_API_BASE=http://host.docker.internal:8083/v1
MORPHEUS_API_KEY=morpheus-local
MORPHEUS_DEFAULT_MODEL=glm-5
On Linux (native Docker), replace host.docker.internal with 172.17.0.1.
Docker Compose
If NanoClaw uses Docker Compose, add extra_hosts to ensure the alias resolves:
services:
nanoclaw:
extra_hosts:
- "host.docker.internal:host-[REDACTED]"
environment:
- MORPHEUS_API_BASE=http://host.docker.internal:8083/v1
- MORPHEUS_API_KEY=morpheus-local
Available Models
| Model | Use Case |
|-------|----------|
| glm-5 | Complex reasoning, coding, analysis (Opus 4.5-level) |
| glm-4.7-flash | Fast responses, lightweight tasks |
| kimi-k2.5 | General purpose |
| qwen3-235b | Large context, multilingual |
Health Check
From inside the container:
curl -sf http://host.docker.internal:8083/health
From the host:
curl -sf http://127.0.0.1:8083/health
Hybrid Routing Strategy
- Use Claude for: orchestration, swarm coordination, complex multi-step tool use
- Use [REDACTED] for: text generation, summarization, research, sub-agent tasks
- Model selection is by name — pass
glm-5orglm-4.7-flashas the model parameter
Staking for Unlimited Inference
cd ~/.everclaw
node scripts/everclaw-wallet.mjs setup
node scripts/everclaw-wallet.mjs stake
MOR tokens are staked, not spent — returned when sessions close. Stake once, use forever.
Related Skills
profbernardoj/buddy-bots
testing
VerifiedTrustedCommunity
Agent-to-agent social coordination. Create a group, every member gets their own buddy bot. Bots talk over XMTP to coordinate real-world actions on behalf of their humans. Built on EverClaw + XMTP + ERC-8004.
110SKILL.mdUpdated May 12, 2026
profbernardoj/archive/alternative-installers/ZeroClaw/workspace/skills/enable-morpheus
data-ai
VerifiedTrustedCommunity
# Enable [REDACTED] — Decentralized Inference for ZeroClaw ## Proxy - **Endpoint:** `http://127.0.0.1:8083/v1` - **Auth:** `morpheus-local` - **Provider URL:** `custom:http://127.0.0.1:8083/v1` ## Models | Config Key | Model | Tier | |------------|-------|------| | `glm5` | GLM-5 (default) | HEAVY | | `flash` | GLM-4.7-flash | LIGHT | | `kimi` | Kimi K2.5 | STANDARD | | `qwen` | Qwen3-235b | STANDARD | ## Switch Model Edit `~/.zeroclaw/config.toml`: ```toml default_model = "glm-4.7-flash"
109SKILL.mdUpdated May 12, 2026
profbernardoj/archive/alternative-installers/TinyClaw/workspace/skills/enable-morpheus
testing
VerifiedTrustedCommunity
# Enable [REDACTED] — Decentralized Inference for TinyClaw ## What This Does Switches TinyClaw agents to use the EverClaw proxy for [REDACTED] decentralized inference. ## When To Use Use `/enable-morpheus` to: - Verify the proxy is running and healthy - Check which models are available - Switch agent model assignments ## Proxy Details - **Endpoint:** `http://127.0.0.1:8083/v1` - **Auth:** `morpheus-local` (Bearer token) - **Health:** `curl -sf http://127.0.0.1:8083/health` ## Available Mo
109SKILL.mdUpdated May 12, 2026
profbernardoj/archive/alternative-installers/PicoClaw/workspace/skills/enable-morpheus
data-ai
VerifiedTrustedCommunity
# Enable [REDACTED] — Decentralized Inference for PicoClaw ## Proxy Details - **Endpoint:** `http://127.0.0.1:8083/v1` - **Auth:** `morpheus-local` - **Health:** `curl -sf http://127.0.0.1:8083/health` ## Models | Name in Config | Model | Use Case | |----------------|-------|----------| | `morpheus-glm5` | GLM-5 | Heavy reasoning, coding (default) | | `morpheus-flash` | GLM-4.7-flash | Fast, lightweight | | `morpheus-kimi` | Kimi K2.5 | General purpose | ## Switch Default Model Edit `~/.pi
109SKILL.mdUpdated May 12, 2026