seraph-agent 0.3.0

The AI agent that audits itself. 26 providers, 42 tools, 22 channels, self-improving.

Seraph

The AI agent that audits itself.

Self-improving, self-auditing, multi-channel AI agent platform. 45 tools, 22 channels, runs everywhere.

Why Seraph?

	OpenClaw	Hermes	Seraph
Self-improving	No	Yes	Yes
Self-auditing	No	No	Yes
Anti-dilution	No	No	Yes
Windows native	Clunky	No (WSL)	Yes
Channels	22	16	22
Tools	~30	48	45
Models	~10	200+	200+
Memory	SQLite	SQLite+FTS5	SQLite+FTS5
Skills guard	No	Regex	Regex + trust scoring
Smart routing	No	Yes	Yes + failover + pool
Canvas	Electron	No	Web (any browser)
Companion app	Native	No	PWA (all platforms)

Install

Quick start (pip):

pip install seraph-agent
seraph onboard

From source:

git clone https://github.com/bosskalash/seraph.git
cd seraph
pip install -e ".[all]"
python3 brain/cli.py onboard

Docker:

git clone https://github.com/bosskalash/seraph.git
cd seraph
cp .env.example .env  # edit with your keys
docker compose up -d

Manual:

git clone https://github.com/bosskalash/seraph.git ~/seraph
cd ~/seraph
pip install requests flask pyyaml openai
# Edit .env with your API keys
python3 run.py

Setup

1. Get an API key from OpenAI or Anthropic
2. Get a Telegram bot token from @BotFather
3. Run seraph onboard or edit .env:

SERAPH_PROVIDER=openai
SERAPH_MODEL=gpt-5.4
OPENAI_API_KEY=your-key-here
SERAPH_TELEGRAM_TOKEN=your-bot-token
SERAPH_ALLOWED_USERS=your-telegram-id

4. Run: python3 run.py
5. Message your bot on Telegram

45 Built-in Tools

Category	Tools
Core	terminal, read_file, write_file, list_files, clipboard
Web	web_search, web_fetch, browse (headless)
Code	run_code (sandbox), apply_patch, audit_file, audit_directory
AI	describe_image (vision), mixture_of_agents, delegate_task, verify_claim
Media	generate_image (DALL-E), text_to_speech, transcribe, voice_respond
Comms	send_email, notify, manage_webhook, send_notification
Data	query_sqlite, export_conversation, export_html, search_sessions
DevOps	ssh, git, git_clone, import_api (OpenAPI), health_check
Smart Home	homeassistant
Workflow	todo, checkpoint, clarify, request_approval, interrupt, progress
Skills	skills_hub (install/search/sync), fuzzy_find, mcp (Model Context Protocol)
Meta	canvas (visual workspace), qr_code, usage_stats

22 Channels

Channel	Protocol	Status
Telegram	Bot API	Production
Discord	Gateway WS	Ready
Slack	Socket Mode	Ready
WhatsApp	Cloud API	Ready
Signal	signal-cli REST	Ready
Matrix	Client-Server	Ready
Email	IMAP + SMTP	Ready
SMS	Twilio	Ready
IRC	Raw socket	Ready
MS Teams	Bot Framework	Ready
Google Chat	Webhook API	Ready
LINE	Messaging API	Ready
Mattermost	REST API	Ready
Twitch	IRC over SSL	Ready
Nostr	Relay protocol	Ready
DingTalk	Robot API	Ready
Feishu/Lark	Open API	Ready
iMessage	BlueBubbles	Ready
WebChat	HTTP server	Ready
Canvas	Visual workspace	Ready
Voice Wake	Mic + wake word	Ready
PWA	Progressive Web App	Ready

40+ Slash Commands

/new         Fresh conversation         /improve     Self-improvement cycle
/model       View or change model       /cron        Manage scheduled jobs
/status      System status              /heartbeat   Health monitor
/tools       List available tools       /doctor      Run diagnostics
/exec        Run a shell command        /approve     DM pairing approval
/search      Search the web             /think       Set reasoning level
/read        Read a file                /insights    Conversation analytics
/files       List workspace files       /update      Pull latest from git
/memory      Memory status              /restart     Restart the bot
/remember    Save a fact                /backup      Backup all data
/forget      Remove a fact              /logs        View recent logs
/recall      Search past conversations  /budget      Daily spending limit
/persona     Switch personality         /template    Prompt templates
/raw         Direct LLM (zero overhead) /config      View/change settings
/sandbox     Run Python code            /compress    Smart compress
/branch      Fork conversation          /retry       Retry last response
/undo        Undo last exchange         /send        Send a file
/checkpoint  Save conversation state    /id          Show Telegram ID
/restore     Restore a checkpoint       /help        Show all commands

Architecture

User (Telegram/Discord/Slack/22 channels)
  |
  v
Gateway (Go) -- HTTP proxy, health, routing
  |
  v
Brain (Python) -- LLM reasoning + 45 tools
  |
  v
SQLite -- memory (FTS5), sessions, skills, rules
  |
  v
Canvas / PWA -- visual workspace + mobile app

What Makes Seraph Different

Anti-Dilution Engine

Other platforms waste 30-50% of context on bloated system prompts. Seraph has:

• Smart tool filtering -- only sends relevant tools per message
• Prompt compiler -- minifies, deduplicates, strips decorations
• Context budget -- system overhead capped at 20%
• Lazy injection -- memory only loaded when conversation needs it
• /raw mode -- zero injection, direct LLM access

Self-Improvement Loop

The agent improves itself over time:

• Reviews conversations for user corrections
• Stores lessons in active memory
• Auto-generates reusable skills from complex tasks
• Self-audits its own code for bugs
• Runs on cron (every 6h) or manual (/improve)

Skills Guard

Every external skill is security-scanned before installation:

• 30+ threat patterns (exfiltration, injection, destructive, credential theft)
• Trust scoring (0-100)
• Install policy by source (builtin/trusted/community)

Canvas

Live visual workspace at http://localhost:18803/canvas. The agent can push HTML, code, tables, charts, and run JavaScript in your browser.

Model Router

• Smart routing -- simple questions use cheap model, complex use strong
• Failover chain -- auto-switch when a model is down
• Credential pool -- rotate API keys with exponential backoff

Configuration

YAML Config (~/.seraph/config.yaml)

model: gpt-5.4
provider: openai
memory:
  enabled: true
skills:
  auto_generate: true
audit:
  enabled: true
  max_rounds: 5

Identity (~/.seraph/SOUL.md)

Customize who your agent is. Injected into every prompt.

MCP Servers (~/.seraph/mcp.json)

{
  "mcpServers": {
    "context7": {
      "command": "npx",
      "args": ["-y", "@upstash/context7-mcp"]
    }
  }
}

Supported Models

• OpenAI: gpt-5.4, gpt-4.1, gpt-4o, gpt-4o-mini
• Anthropic: claude-opus-4-6, claude-sonnet-4-6, claude-haiku-4-5
• OpenRouter: 200+ models via one API key

Testing

pip install -e ".[dev]"
python -m pytest tests/ -v

License

MIT