simpler

Author: illeatmyhat

.env.example

@@ -1,14 +1,14 @@
 # Required: API key for LLM access
 OPENAI_API_KEY="<YOUR_OPENAI_API_KEY>"
 
-# Optional: ALTK-Evolve Backend Configuration
-# ALTK_EVOLVE_BACKEND=filesystem
-# ALTK_EVOLVE_NAMESPACE_ID=altk-evolve
+# Optional: Evolve Backend Configuration
+# EVOLVE_BACKEND=filesystem
+# EVOLVE_NAMESPACE_ID=evolve
 
 # Optional: LLM Configuration
-# ALTK_EVOLVE_MODEL_NAME=gpt-4o
-# ALTK_EVOLVE_CUSTOM_LLM_PROVIDER=openai
+# EVOLVE_MODEL_NAME=gpt-4o
+# EVOLVE_CUSTOM_LLM_PROVIDER=openai
 # OPENAI_BASE_URL=https://api.openai.com/v1
 
 # Optional: Advanced Settings
-# ALTK_EVOLVE_CLUSTERING_THRESHOLD=0.80
+# EVOLVE_CLUSTERING_THRESHOLD=0.80

.github/workflows/docker-publish.yml

@@ -34,7 +34,7 @@ jobs:
         id: meta
         uses: docker/metadata-action@v5
         with:
-          images: ${{ secrets.DOCKERHUB_USERNAME }}/altk-evolve
+          images: ${{ secrets.DOCKERHUB_USERNAME }}/evolve
           flavor: |
             suffix=-${{ matrix.image-suffix }},onlatest=true
           tags: |
@@ -60,5 +60,5 @@ jobs:
         with:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
-          repository: ${{ secrets.DOCKERHUB_USERNAME }}/altk-evolve
+          repository: ${{ secrets.DOCKERHUB_USERNAME }}/evolve
           readme-filepath: ./README.md

.github/workflows/python-publish.yml

@@ -14,7 +14,7 @@ jobs:
       id-token: write
     environment:
       name: pypi
-      url: https://pypi.org/project/altk-evolve
+      url: https://pypi.org/project/evolve
     steps:
       - name: Download release assets
         env:

.gitignore

@@ -6,12 +6,12 @@
 *.db*
 .DS_Store
 __pycache__
-altk_evolve_data
+evolve_data
 demo/workdir/.claude/
 .bob
 .claude
 dist
 .coverage
-/.altk-evolve
+/.evolve
 .secrets
 event.json

.roomodes

@@ -1,22 +1,22 @@
 {
   "customModes": [
     {
-      "slug": "altk-evolve",
-      "name": "ALTK-Evolve",
-      "roleDefinition": "You are the ALTK-Evolve agent \u2014 a self-improving AI assistant deeply familiar with the ALTK-Evolve project. Your purpose is to help the project continuously improve by extracting lessons from work done, storing them as searchable guidelines in the ALTK-Evolve vector database, and surfacing those learnings to improve project documentation. You have full knowledge of the ALTK-Evolve CLI (`uv run altk-evolve`) and the project's architecture as described in AGENTS.md.",
-      "customInstructions": "See .roo/rules-altk-evolve/instructions.md for detailed behavior for each slash command.",
+      "slug": "evolve",
+      "name": "Evolve",
+      "roleDefinition": "You are the Evolve agent \u2014 a self-improving AI assistant deeply familiar with the Evolve project. Your purpose is to help the project continuously improve by extracting lessons from work done, storing them as searchable guidelines in the Evolve vector database, and surfacing those learnings to improve project documentation. You have full knowledge of the Evolve CLI (`uv run evolve`) and the project's architecture as described in AGENTS.md.",
+      "customInstructions": "See .roo/rules-evolve/instructions.md for detailed behavior for each slash command.",
       "groups": [
         "read",
         "edit",
         "command"
       ]
     },
     {
-      "slug": "altk-evolve-lite",
-      "name": "ALTK-Evolve Lite",
-      "firstMessage": "\u26a0\ufe0f MANDATORY WORKFLOW: I MUST call altk-evolve-recall FIRST before any other action, then complete your request, then call altk-evolve-learn BEFORE attempt_completion. This workflow is NON-NEGOTIABLE.",
-      "roleDefinition": "You are ALTK-Evolve Lite \u2014 a learning mode that improves from every interaction.",
-      "customInstructions": "- ALWAYS read a skill's SKILL.md before using it for the first time in a conversation\n- If altk-evolve-recall returns no guidelines, that is normal \u2014 proceed with the task.\n- If altk-evolve-learn reports no new entities, that counts as successful completion \u2014 do not retry.\n- If no errors or non-obvious discoveries occurred, saving zero entities is correct \u2014 do not force low-quality entities.",
+      "slug": "evolve-lite",
+      "name": "Evolve Lite",
+      "firstMessage": "\u26a0\ufe0f MANDATORY WORKFLOW: I MUST call evolve-recall FIRST before any other action, then complete your request, then call evolve-learn BEFORE attempt_completion. This workflow is NON-NEGOTIABLE.",
+      "roleDefinition": "You are Evolve Lite \u2014 a learning mode that improves from every interaction.",
+      "customInstructions": "- ALWAYS read a skill's SKILL.md before using it for the first time in a conversation\n- If evolve-recall returns no guidelines, that is normal \u2014 proceed with the task.\n- If evolve-learn reports no new entities, that counts as successful completion \u2014 do not retry.\n- If no errors or non-obvious discoveries occurred, saving zero entities is correct \u2014 do not force low-quality entities.",
       "groups": [
         "read",
         "edit",

AGENTS.md

@@ -1,5 +1,5 @@
-# What is ALTK-Evolve?
-ALTK-Evolve is a Python library and service which enables AI agents to improve through self-reflection.
+# What is Evolve?
+Evolve is a Python library and service which enables AI agents to improve through self-reflection.
 
 ## Key Concepts
 - **Trajectory**: A recorded agent conversation
@@ -10,9 +10,9 @@ ALTK-Evolve is a Python library and service which enables AI agents to improve t
 
 ## Architecture Flow
 1. Agent completes some task, and the resulting trajectory is automatically saved into a logging framework such as Langfuse or Arize Phoenix.
-2. The agent can call the sync MCP function, or the user can manually sync, which causes altk-evolve to process the trajectory and save any generated guidelines.
+2. The agent can call the sync MCP function, or the user can manually sync, which causes evolve to process the trajectory and save any generated guidelines.
 3. Generated guidelines are stored as entities with conflict resolution applied.
-4. Future agents can query the ALTK-Evolve MCP server to fetch guidelines for similar tasks
+4. Future agents can query the Evolve MCP server to fetch guidelines for similar tasks
 
 ## Project Directory Tree (Some files omitted for brevity)
 ```text
@@ -23,7 +23,7 @@ ALTK-Evolve is a Python library and service which enables AI agents to improve t
 ├── docs (Data used by README files)
 ├── explorations (Tangential projects for feeling out future work. Should be avoided unless otherwise prompted.)
 │   └── claudecode
-├── altk-evolve (Primary Source Root)
+├── evolve (Primary Source Root)
 │   ├── backend (Entity Database Backend implementations, primarily vector databases)
 │   ├── cli (A CLI wrapper over the native Python client)
 │   ├── config (All configurations which are derived from environment variables or instantiated as an object)
@@ -35,15 +35,15 @@ ALTK-Evolve is a Python library and service which enables AI agents to improve t
 │   ├── schema (All well-defined datatypes used throughout the project)
 │   ├── sync (Upstream data sources to be processed and stored in the backend)
 │   └── utils (Small reusable code snippets)
-├── tests (All tests for altk-evolve)
+├── tests (All tests for evolve)
 ├── .env.example (Environment variable template file)
-└── .env (Environment variables used to configure altk-evolve)
+└── .env (Environment variables used to configure evolve)
 ```
 
 ## First Time Setup
 ```bash
 uv sync && source .venv/bin/activate
-cp .env.example .env  # Configure any environment variables, defined in `./altk-evolve/config`
+cp .env.example .env  # Configure any environment variables, defined in `./evolve/config`
 pre-commit install
 ```
 
@@ -60,9 +60,9 @@ pre-commit install
 
 ## Available Interfaces
 - MCP Server: `get_entities()`, `get_guidelines()`, `save_trajectory()`
-- CLI: Run `altk-evolve --help` if details are needed about its subcommands.
+- CLI: Run `evolve --help` if details are needed about its subcommands.
   Available subcommands include `namespaces`, `entities`, and `sync`
-- Python Client: `ALTKEvolveClient()` for programmatic access
+- Python Client: `EvolveClient()` for programmatic access
 
 ## Coding Standards
 - Use Ruff for linting and formatting (configured in pyproject.toml)