loopx
The control plane for 24/7 always-on agents. Turn long-horizon goals into verifiable results across Codex, Claude Code, and custom runtimes—from local SQLite to team scale.
- 6.7k
- Python
- Apache-2.0
- 9 h ago
The control plane for 24/7 always-on agents. Turn long-horizon goals into verifiable results across Codex, Claude Code, and custom runtimes—from local SQLite to team scale.
The Harness of Harnesses • Super Agent: a trusted, persistent, self-evolving multi-agent ecosystem for all-domain collaboration.
An open-source document parsing model with SOTA accuracy and speed, using an RSI loop during post-training.
PhyAgentOS is a Recursive Self-Improving (RSI) physical agent operating system that enables agents to recursively self-improve through agentic workflows.
Formal verification for AI: a Lean 4 + Dafny proof checker that catches fake AI proofs (reward hacking), and verified recursive self-improvement (RSI) for coding agents. AI for math, physics and software engineering.
NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness.
An RSI Agent Harness for running, evaluating, and evolving agents—with tools, skills, MCP, stateful execution, and multi-agent workflows.
A curated research map of Recursive Self-Improvement (RSI): models, agents, harnesses, embodied systems, automated AI R&D, benchmarks, and safety.
Technical indicators to run technical analysis with JavaScript & TypeScript. 📈
💹 Simple HTML Snippets to create Tickers / Charts of Cryptocurrencies with the TradingView API 💹
📺 A Dashboard with the price movements of Cryptocurrencies 💹
Verifiable handwriting synthesis for feedback-driven model improvement and RSI research. Seeded examples, artifact checks and auditable data handoffs.
Recursive Experiential–Working Memory Evolution for Long-Horizon Agent Harnesses
Fewer Tokens, Better Action: GPT-6 Astra Robot Agents with 14% Higher Success but 65% Fewer Tokens
[Public preview] Externally scored agentic ML research benchmark: 60 tasks, real competition ground truth. Open protocol, operated evaluation.
The open-source design agent and harness, better than Claude Design on academic communication artifacts production. This DesignHarness can also be used with any coding harness you like ( Codex/Claude Code/Kimi Code/Pi/OpenCode etc..) and any agentic model you want.
💹 Forex charts with the USD price movements of currencies 💹
🌕 Gold/Silver ratio metal charts with the USD/CHF price movements of Gold/Silver 🌑
RSIGame: Autonomous agentic game development with recursive self-improvement
[EMNLP 2026] LightRSI is a modular runtime for lightly deploying recursive self-improvement loops in long-horizon LLM agents.
Human-feedback and data-governance infrastructure for RSI research: annotation, review, provenance and frozen dataset candidates.
Python toolkit for MinT, the open infrastructure for experiential intelligence and LoRA RL.
🇨🇭 Swiss Leader Index SLI charts with the CHF/USD price movements of top stocks 💹
Technical Indicators implemented in Python only using Numpy-Pandas as Magic - Very Very Fast! Very tiny! Stock Market Financial Technical Analysis Python library . Quant Trading automation or cryptocoin exchange
A desktop coding workspace for AI agents — chat, files, editor, terminal, Git worktrees and browser preview, plus bounded, evidence-driven Recursive Self-Improvement (RSI). Electron + React + TypeScript.
A recursive self-improvement (RSI) workflow that evolves both target agents (e.g., Pi and DeepSeek Harness) and the RSI system itself.
Run a coding model at 300+ tok/s on your Mac. Native Rust + Metal inference engine for LiquidAI LFM2.5-24B-A2B (MLX 4-bit) on Apple Silicon.
Modern Go library for taapi.io technical analysis API. Features fluent interface, type-safe enums, comprehensive error handling, and full API coverage. Supports direct indicators, bulk requests, and manual calculations with custom candle data. Production-ready with complete test coverage and zero dependencies. Golang
Idiomatic Go client library for Marketstack API. Provides easy access to real-time, intraday, and historical stock market data from 70+ global exchanges. Features context support, type-safe requests/responses, comprehensive tests (75.8% coverage), and production-ready error handling. MIT licensed.
Modern PHP/Laravel library for taapi.io technical analysis API. Features fluent interface, PHP 8.1+ enums, strict typing, comprehensive error handling, and full Laravel integration. Supports direct indicators, bulk requests, and manual calculations with custom candle data. Production-ready with complete test coverage.
天天养基是全网最好用的基金实时估值股票量化系统,盘中基金估值,实时估值,基金净值,养基宝,小倍养基,Open-source fund valuation & quant trading platform — real-time QDII NAV, MACD/RSI signals, AI tools. 开源基金估值与量化模拟平台