Core library for building type-safe LLM applications with structured input/output signatures, automatic validation, and reasoning patterns within TypeScript
AI-guided LLM optimization. Install → Tell Claude 'Read .claude/agents/iris.md' → Claude becomes your optimization guide. DSPy prompts, Ax hyperparameters, local LLMs, federated learning. You talk, Iris handles the rest.
Hal9: Create and Share Generative Apps
OpenAI ChatGPT integration for TS-DSPy - enables type-safe LLM interactions with GPT-3.5, GPT-4, and other OpenAI models for TypeScript
Production-ready examples for @ruvector/agentic-synth - DSPy training, multi-model benchmarking, and advanced synthetic data generation patterns
SDK for LLM pipelines with OpenCode, Codex, and Zod
Gemini API integration for TS-DSPy - enables type-safe LLM interactions with Gemini models for TypeScript
Node ↔ Python bridge for DSPy. Spawns a uv-pinned Python sub-process that hosts compiled DSPy programs and answers JSON-line RPC. Substrate pick #1 of the AI tech modernization proposal §6.
No description provided.
No description provided.
Close the eval-to-improvement loop for promptfoo. Automatically evaluate, identify low-scoring prompts, rewrite with any LLM, and re-evaluate.
Effect-native DSPy — programming, not prompting, language models
OpenTelemetry SpanProcessor for atrib. Reads OpenInference-shaped spans and emits signed atrib records on a parallel pipeline. One integration reaches every framework with OpenInference instrumentation.
CLI tool to scan codebases for LLM SDK usage, AI frameworks, and exposed API tokens
Pi package inspired by Hermes Agent Self-Evolution for reflective improvement of skills, prompts, and instruction files.
Shared TypeScript types for Cogitator
CLI for promptc.
Security-focused `SKILL.md` packs for reviewing and hardening LLM systems.
A 1:1 TypeScript alternative to DSPy — Declarative Self-improving Language Programs
Cognitive-driven multi-agent orchestration for society.db, prompt-vault, and agent-kernel
AI agent with an internal ecology of strategies that compete and evolve based on real task performance
TypeScript implementation of GEPA (Gradient-free Evolution of Prompts and Agents) - Complete port with 100% feature parity
Find every AI agent in your codebase. Zero config, zero dependencies. Just run npx arkna-scan.
Versalist CLI with built-in MCP server mode for challenge workflows and agent-native coding environments