Search

IVVO AgileAgent — Instalador CLI de agentes de IA para times de desenvolvimento

The Conductor for AI Agents — Multi-Agent Execution System with Task, Roles & Orchestration

Pane-embeddable coding agent. Ships direct/local/vercel-sandbox execution modes behind one interface.

Scaffold AI agent-friendly documentation in any repository

Run Claude Code agents overnight on your codebase. Interactive terminal UI (Ink) + bash harness + Claude Code skill + slash commands. Write a todo file with Implementation+Validation pairs, launch, wake up to validated code.

[Future Scope - Do not use until v1.0.0] Hugging Face Inference API client wrapper for GlimLang

Open-source Python port of Claude Code - an AI-powered CLI coding assistant

Your local AI brain: persistent memory + full observability for any model. Data never leaves your machine.

AST+vector context router for AI coding agents — cut token costs 5-15x

Deterministic security sidecar for LLM agent frameworks

KRYTH CLI: Autonomous Coding Intelligence — terminal AI coding agent with tools, sessions, and OpenAI-compatible model support

Zero-LLM memory for AI agents — semantic search, cross-encoder reranking, and deterministic heuristics

Agent-native trace SDK for LangChain / LangGraph / deepagents (skeleton)

Autonomous research-aware iteration agent for ML models and LLM prompts. Multi-LLM backend (Claude/GPT/Llama/Deepseek), persistent memory, literature-grounded experiments, human-approval safety gates.

Letta tools for the Ejentum Reasoning Harness. Eight agent-callable functions registered with a Letta server via tools.upsert_from_function: four dynamic (reasoning, code, anti_deception, memory) and four adaptive (adaptive_reasoning, adaptive_code, adaptive_anti_deception, adaptive_memory) that pre-fit the operation to the task via an adapter LLM. Each call returns a structured cognitive injection: a natural-language procedure plus an executable reasoning topology.

smolagents Tool subclasses for the Ejentum Reasoning Harness. Eight tools: four dynamic (reasoning, code, anti-deception, memory) and four adaptive (adaptive-reasoning, adaptive-code, adaptive-anti-deception, adaptive-memory) that pre-fit the operation to the task via an adapter LLM. Each call returns a structured cognitive injection: a natural-language procedure plus an executable reasoning topology.

PydanticAI toolset for the Ejentum Reasoning Harness. EjentumToolset subclasses pydantic_ai.FunctionToolset and registers eight tools: four dynamic (reasoning, code, anti-deception, memory) plus four adaptive variants (adaptive-reasoning, adaptive-code, adaptive-anti-deception, adaptive-memory) that pre-fit the cognitive operation to the caller's task via an adapter LLM.

Python library wrapping Jina AI Reader: convert URLs, search results, and files into LLM-friendly Markdown.

EvalKit Python SDK — LLM observability and tracing

Universal TIBET provenance for ANY Python code. @tibet_guard decorator, ASGI middleware, agent safety. OWASP LLM06 compliant.