Back to browse
GitHub Repository

An intent-based language for agentic systems. Write agents in English. Transpile to async Python.

0 starsPython

Drift, write LLM agents in English and transpile to async Python

by rileyq12·Jun 28, 2026·2 points·0 comments

AI Analysis

●●●BangerBig BrainZero to One

Transpiles English-like agent DSL to Python with confidence-gated branching and budget controls.

Strengths
  • Transpiler architecture is novel compared to typical API-chaining agent frameworks.
  • Confidence-gated branching (confident<T>) enables cheap-path-first escalation patterns.
  • Budget controls and multi-provider routing at language level, not runtime config.
Weaknesses
  • Agent DSLs exist (LangGraph, CrewAI) — needs clear differentiation beyond syntax.
  • Adoption depends on ecosystem — MCP support helps but tooling maturity unclear.
Category
Target Audience

Developers building LLM agent workflows

Similar To

LangGraph · CrewAI · AutoGen

Similar Projects

AI/ML●●Solid

AgentForge – Multi-LLM Orchestrator in 15KB of Python

AgentForge compresses common production patterns—token-aware rate limiting (token-bucket), retry+exponential backoff, prompt templates and cost tracking—into a tiny async core and lets you flip providers with one parameter. The multi-agent mesh and ReAct loop bits are the most interesting engineering bets here, and the repo includes benchmarks and a Streamlit demo, but it lives in a crowded space next to LangChain and similar toolkits so real differentiation will come from adoption and edge-case robustness.

Niche GemShip It
chunktort
214mo ago
AI/ML●●Solid

AgentForge – Multi-LLM Orchestrator in 15KB

AgentForge packs provider adapters (Claude, GPT‑4, Gemini, Perplexity), token-aware rate limiting, retry/backoff, and a MockLLMClient for tests into a tiny dependency surface — the 15KB footprint and 2 dependencies is an attention-grabber. The 3‑tier Redis cache and benchmark claims (huge latency/memory wins vs LangChain, 88% cache hit) make it a tempting low-overhead alternative, though you should validate provider feature parity and benchmarks against your workload.

Dark HorseWizardry
chunktort
104mo ago