Search results for "jsonl"
Modern high-performance serialization utilities for Python
LLM-powered knowledge base from your Claude Code, Codex CLI, Copilot, Cursor & Gemini sessions. Karpathy's LLM Wiki pattern — implemented and shipped.
One brain, many harnesses. Portable .agent/ folder (memory + skills + protocols) that plugs into Claude Code, Cursor, Windsurf, OpenCode, OpenClaw, Hermes, or DIY Python — and keeps its knowledge when
Cognithor - Agent OS: Local-first autonomous agent operating system. 16 LLM providers, 17 channels, 112+ MCP tools, 5-tier memory, A2A protocol, knowledge vault, voice, browser automation, Computer-us
Most advanced AI coworker
ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works wi
AI-first security scanner with 76 analyzers, 9,600+ detection rules, and repo poisoning detection for AI/ML, LLM agents, and MCP servers. Scan any GitHub repo with: medusa scan --git user/repo
Brain-inspired knowledge graph: spreading activation, Hebbian learning, memory consolidation.
The official Python library for the OpenAI API
AINL helps turn AI from "a smart conversation" into "a structured worker." It is designed for teams building AI workflows that need multiple steps, state and memory, tool use, repeatable execution, v
Enterprise-ready MCP Gateway & Registry that centralizes AI development tools with secure OAuth authentication, dynamic tool discovery, and unified access for both autonomous AI agents and AI coding a
The implementation for SIGIR 2026: Learning to Retrieve from Agent Trajectories.
Project-agnostic, composable AI workflow automation via pi packages and Claude Code plugins.
See how you really use AI — X-ray your AI coding sessions locally
Python ETL framework for stream processing, real-time analytics, LLM pipelines, and RAG.
PinchBench is a benchmarking system for evaluating LLM models as OpenClaw coding agents. Made with 🦀 by the humans at https://kilo.ai
Open security scanner for AI supply chain: agents, MCP, containers, cloud, GPU, and runtime with blast-radius analysis.
RAGElo is a set of tools that helps you selecting the best RAG-based LLM agents by using an Elo ranker
Universal LLM Gateway: One API, every LLM. OpenAI/Anthropic-compatible endpoints with multi-provider translation and intelligent load-balancing.
"DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)"
Unified framework for building enterprise RAG pipelines with small, specialized models
A-RAG: Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces. State-of-the-art RAG framework with keyword, semantic, and chunk read tools for multi-hop QA.
3-tier agentic ChatOps (n8n + GPT-4o + Claude Code) implementing all 21 patterns from "Agentic Design Patterns" — solo operator managing 137 devices
Autonomous Offensive Security Intelligence AI-powered multi-agent penetration testing
The Next-Gen Agent-Native Skill Recommendation Engine
Framework for AI agents to build and maintain an Obsidian wiki using Karpathy's LLM Wiki pattern
Open-Source Intelligent Command Layer
Agentic AI assistant on Telegram, powered by Claude Code. Runs locally with shell access, spec-driven PR reviews, layered security, persistent memory, and scheduled jobs. Your machine, your data, your
MoralStack is a governance and safety layer for LLM applications. It analyzes user requests before generation, evaluates risk and intent, and decides whether the AI should answer normally, answer safe
Open-Sable is a local-first autonomous agent framework with AGI-inspired cognitive subsystems (goals, memory, metacognition, tool use). It can run continuously on your machine, integrate with chat int
A self-improving AI agent that learns from experience. Runs entirely on a local 9B model. Security by absence — dangerous capabilities were never built.
Autonomous VAPT platform. Give it a target (FQDN, IP, CIDR) — it hunts, it reports. Inspired by the Obsidian Order.
Continuous prompt optimization for AI applications. Collect feedback, auto-optimize with DSPy, deliver as reviewable PRs.
Connect any LLM to OpenClaw — production-tested middleware for Qwen3-235B and beyond
Self-evolving AI agent framework with 5-layer safety gatekeeper. Agents observe failures, propose fixes, and safely apply them. Built on HKUDS/nanobot.
AI co-pilot for ComfyUI — 113 tools for workflow authoring, model provisioning, and iterative rendering. Multi-provider (Claude, GPT-4o, Gemini, Ollama). Ships as MCP server or standalone CLI.
🦾 A production‑ready research outreach AI agent that plans, discovers, reasons, uses tools, auto‑builds cited briefings, and drafts tailored emails with tool‑chaining, memory, tests, and turnkey Dock
HealthFlow: A Self-Evolving AI Agent with Meta Planning for Autonomous Healthcare Research