ignite-ember 0.3.7

Terminal-based AI coding assistant built on Agno

Ember Code

One spark ignites a team. An AI coding assistant built with Agno orchestration.

ignite-ember.sh

Inspired by Claude Code, Ember Code is a terminal-based coding agent that assembles specialized AI teams on the fly. Describe your task — the Orchestrator picks the right agents, the right team mode, and runs them.

Why Ember Code?

Claude Code uses a single agent loop — powerful but monolithic. Ember Code takes a different approach: dynamic multi-agent orchestration. Instead of one agent doing everything, Agno's team system decomposes tasks, routes them to specialized agents, and synthesizes results — all automatically.

Feature	Claude Code	Ember Code
Architecture	Single agent loop	Multi-agent teams (Agno)
Task routing	Manual sub-agent spawning	Automatic via Coordinate/Route modes
Code intelligence	Grep + file reads	CodeIndex semantic search (included free)
Knowledge base	None	ChromaDB vector store with custom embeddings
Planning	Plan mode (read-only)	Agno reasoning + Tasks mode
IDE integration	MCP server (stdio)	MCP server + client (Agno MCPTools)
Extensibility	Plugins, hooks, MCP	Agents + hooks + toolkits + MCP
Agent evals	Not built-in	Built-in regression testing framework
Memory	File-based MEMORY.md	Agno Memory + DB-backed storage
Learning	None	Agno LearningMachine (user profiles, entity memory)
Guardrails	None	PII detection, prompt injection, moderation
HITL	Implicit	Explicit confirmation/input requirements
Default model	Anthropic Claude	MiniMax M2.7 (model-agnostic, swappable)

Quick Start

brew install ignite-ember/tap/ignite-ember  # or: pip install ignite-ember
ignite-ember /login              # sign up for hosted models (MiniMax M2.7)
ignite-ember                     # start coding

Or bring your own model (OpenAI, Anthropic, Groq, Ollama, etc.):

export OPENAI_API_KEY=sk-...

# .ember/config.yaml
models:
  default: gpt-4o
  registry:
    gpt-4o:
      provider: openai_like
      model_id: gpt-4o
      url: https://api.openai.com/v1
      api_key: sk-...              # direct key in config
      # api_key_env: OPENAI_API_KEY  # or from env var
      # api_key_cmd: "op read ..."   # or from shell command

See Quickstart for the full setup guide.

Upgrading

v0.3.7 includes the following changes:

• Problem: Edit/Write/Bash tools never asked for user confirmation, even when permissions were set to "ask".
  • Solution: requires_confirmation flag is now set on each function after registration in all custom toolkits.

v0.3.6 includes the following changes:

• Problem: Debug logs grow unbounded and can fill up disk space.

  • Solution: Switched to RotatingFileHandler with 10MB limit and 2 backup files.

• Problem: Shell command output can be extremely large, causing issues when sending to the LLM.

  • Solution: Truncate tool results to 30,000 characters, keeping start and end of output.

• Problem: TUI escape key only closes the login dialog, leaving other panels open.

  • Solution: Now closes any open panel: login, help, model picker, or session picker.

• Problem: Learning features get stuck and never complete (caused by httpx connection pool issues in threads).

  • Solution: Run learning extraction as an async task on the main event loop instead of a separate thread.

To upgrade Ember Code to the latest version:

brew upgrade ignite-ember/tap/ignite-ember

If brew upgrade doesn't work or you encounter issues, manually reinstall:

brew uninstall ignite-ember && brew untap ignite-ember/tap && brew tap ignite-ember/tap && brew install ignite-ember

TUI Mode

ignite-ember launches the Textual-based terminal UI by default. The backend runs as a separate process, connected via Unix socket.

Features: streaming responses, agent tree visualization, token tracking, session picker, keyboard shortcuts, HITL confirmation dialogs.

IDE Integration

Ember Code integrates with IDEs via the Model Context Protocol (MCP):

{
  "mcpServers": {
    "ignite-ember": {
      "type": "stdio",
      "command": "ignite-ember",
      "args": ["mcp", "serve"]
    }
  }
}

Works with VS Code, JetBrains (IntelliJ, PyCharm, etc.), Cursor, and Windsurf. See MCP docs for details.

Key Features

Knowledge Base

Built-in vector knowledge base powered by ChromaDB and the Ember embeddings API:

knowledge:
  enabled: true
  collection_name: "my_project"
  embedder: "local"             # local SentenceTransformer (or "ember" for cloud)

Add content via slash commands: /knowledge add <url|path|text>, search with /knowledge search <query>. Agents can search the knowledge base automatically during execution.

Learning & Reasoning

• Learning — Agno LearningMachine builds user profiles, entity memory, and session context across conversations
• Reasoning tools — think and analyze tools for step-by-step reasoning during complex tasks

Guardrails

Built-in safety guardrails via Agno's pre-hook system:

guardrails:
  pii_detection: true          # detect and flag PII in prompts
  prompt_injection: true       # detect injection attempts
  moderation: true             # OpenAI moderation API

Human-in-the-Loop (HITL)

Agents can pause execution to request confirmation or user input before proceeding with sensitive operations. The TUI shows interactive approval dialogs.

Documentation

• Quickstart — Get up and running in under 5 minutes
• Architecture — System design and agent topology
• Agents — Specialized agents and their roles
• Skills — Reusable prompted workflows (/deploy, /review-pr, etc.)
• Onboarding — First-run setup, CodeIndex, and agent proposals
• Tools — Available toolkits and capabilities
• MCP — IDE integration via Model Context Protocol
• Configuration — Settings, permissions, and customization
• CodeIndex — Semantic code intelligence engine
• Evals — Agent evaluation framework and regression testing
• Hooks — Pre/post tool execution hooks
• Migration — Coming from Claude Code or Codex
• Security — Threat model, permissions, and enterprise hardening
• Development — Contributing and extending Ember Code

License

MIT