| name | agent-platform |
|---|---|
| version | 0.1.0 |
| description | Self-developing AI agent platform with multi-provider routing, RAG, skills, and workflow orchestration. Processes raw user inputs to autonomously build agent-based solutions. |
| author | aleksandr |
| created | 2025-02-01 |
- Name: Agent Platform
- Purpose: Autonomous agent development and execution platform
- Philosophy: Bootstrap-first, cost-optimized, locally-first with cloud scale path
- Input Processing: Accepts markdown, CSV, DOCX, TXT, audio transcripts, conversation dumps
- Intent Understanding: Extracts user goals, constraints, and context from raw inputs via RAG
- Autonomous Planning: Generates implementation plans requiring human approval before execution
- Agent Development: Creates and deploys agent workflows, skills, and integrations
- Multi-Provider LLM Routing: Routes to cheapest viable model (local → cheap API → premium API)
- Skill Management: Discovers, loads, and executes AgentSkills (SKILL.md standard)
- Memory System: Short-term (context), long-term (semantic), episodic (history)
- RAG System: Local document ingestion with ChromaDB + Ollama embeddings
- MCP Integration: Connects to external tools via Model Context Protocol
- Workflow Orchestration: DAG-based multi-step workflow execution with checkpointing
- Local Ollama (qwen2.5-coder:14b, deepseek-coder-v2:16b) — $0
- Gemini Flash / Deepseek API — budget tier
- Claude Sonnet / GPT-4o — quality tier (final outputs only)
- All data stays local by default
- Human approval gate before any execution phase
- Every operation is logged with cost tracking
- Skills follow Anthropic's SKILL.md standard (agentskills.io)
- Workflows are defined as YAML, executed as DAGs
- Memory consolidation runs after every 10 interactions
- All Python files include type hints
- All modules include docstrings
- Configuration via .env (never hardcoded)
- Tests mirror source structure under tests/