altk-evolve 1.0.8

Add your description here

Evolve: On‑the‑job learning for AI agents

Blog posts: IBM announcement | Hugging Face blog

Evolve is a system designed to help agents improve over time by learning from their trajectories. It uses a combination of an MCP server for tool integration, vector storage for memory, and LLM-based conflict resolution to refine its knowledge base.

[!IMPORTANT] ⭐ Star the repo: it helps others discover it.

Features

• MCP Server: Exposes tools to get guidelines and save trajectories.
• Conflict Resolution: Intelligently merges new insights with existing guidelines using LLMs.
• Trajectory Analysis: Automatically analyzes agent trajectories to generate guidelines and best practices.
• Milvus Integration: Uses Milvus (or Milvus Lite) for efficient vector storage and retrieval.

Architecture

Quick Start

Installation

Prerequisites:

• Python 3.12 or higher
• uv (recommended) or pip

git clone <repository_url>
cd altk-evolve
uv venv --python=3.12 && source .venv/bin/activate
uv sync

Configuration

For direct OpenAI usage:

export OPENAI_API_KEY=sk-...

For LiteLLM proxy usage and model selection (including global fallback via EVOLVE_MODEL_NAME), see the configuration guide.

Running the MCP Server & UI

Evolve provides both a standard MCP server and a full Web UI (Dashboard & Entity Explorer).

[!IMPORTANT] Building from Source: If you cloned this repository (rather than installing a pre-built package), you must build the UI before it can be served.

cd altk_evolve/frontend/ui
npm ci && npm run build
cd ../../../

See altk_evolve/frontend/ui/README.md for more frontend development details.

Starting Both Automatically

The easiest way to start both the MCP Server (on standard input/output) and the HTTP UI backend is to run the exported launcher:

uv run evolve-mcp

This will start the UI server in the background on port 8000 and the MCP server in the foreground. You can then access the UI locally by opening your browser to: http://127.0.0.1:8000/ui/

Starting the UI Standalone

If you only want to access the Web UI and API (without the MCP server stdio blocking the terminal), you can run the FastAPI application directly using uvicorn:

uv run uvicorn altk_evolve.frontend.mcp.mcp_server:app --host 127.0.0.1 --port 8000

Then navigate to http://127.0.0.1:8000/ui/.

Starting only the MCP Server

If you're attaching Evolve to an MCP client that requires a direct command (like Claude Desktop):

uv run evolve-mcp

Or for SSE transport:

uv run evolve-mcp --transport sse --port 8201

Verify it's running:

npx @modelcontextprotocol/inspector@latest http://127.0.0.1:8201/sse --cli --method tools/list

Available tools:

• get_entities(task: str, entity_type: str): Get relevant entities for a specific task, filtered by type (e.g., 'guideline', 'policy').
• get_guidelines(task: str): Get relevant guidelines for a specific task (backward compatibility alias).
• save_trajectory(trajectory_data: str, task_id: str | None): Save a conversation trajectory and generate new guidelines.
• create_entity(content: str, entity_type: str, metadata: str | None, enable_conflict_resolution: bool): Create a single entity in the namespace.
• delete_entity(entity_id: str): Delete a specific entity by its ID.

Tip Provenance

Evolve automatically tracks the origin of every guideline it generates or stores. Every tip entity contains metadata identifying its source:

• creation_mode: Identifies how the tip was created (auto-phoenix via trace observability, auto-mcp via trajectory saving tools, or manual).
• source_task_id: The ID of the original trace or task that inspired the tip, providing full audibility.

See the Low-Code Tracing Guide for more details.

Community & Feedback

Evolve is an active project, and real‑world usage helps guide its direction.

If you’re experimenting with Evolve or exploring on‑the‑job learning for agents, feel free to open an issue or discussion to share use cases, ideas, or feedback.

Documentation

• Documentation Home - Overview of guides, reference docs, and tutorials
• Installation - Setup instructions for supported platforms
• Configuration - Environment variables and backend options
• CLI Reference - Command-line interface documentation
• Evolve Lite - Lightweight Claude Code plugin mode
• Claude Code Demo - End-to-end demo walkthrough
• Policies - Policy support and schema

Development

Running Tests

The test suite is organized into 4 cleanly isolated tiers depending on infrastructure requirements:

1. Default Local Suite Runs both fast logic tests (unit) and filesystem script verifications (platform_integrations).

   uv run pytest
   

2. Unit Tests (Only) Fast, fully-mocked tests verifying core logic and offline pipeline schemas.

   uv run pytest -m unit
   

3. Platform Integration Tests Fast filesystem-level integration tests verifying local tool installation and idempotency.

   uv run pytest -m platform_integrations
   

4. End-to-End Infrastructure Tests Heavy tests that autonomously spin up a background Phoenix server and simulate full agent workflows.

   uv run pytest -m e2e --run-e2e
   

   (See the Low-Code Tracing Guide for more details).

5. LLM Evaluation Tests Tests needing active LLM inference to test resolution pipelines (requires LLM API keys).

   uv run pytest -m llm