#tool-use

Python implementation of coding agent core mechanisms, with architecture comparison across Claude Code / Kimi Code / Codex

Evidence router & policy engine for coding agents — enforces source choice and proof-of-use through Claude Code hooks, including routes to MCP tools. Local-first; no LLM in the hook loop.

LLM-powered agent that answers questions over a SQL database using tools

An autonomous, LLM-powered SRE agent that takes production incidents from alert to fix/pulls metrics and logs, diagnoses the root cause, runs remediation, and writes the incident report.

AI agent that researches any company and produces a structured PDF risk report using Claude's tool-use API

Same agent action, safe or dangerous by context: email team vs investor; delete scratch vs prod config. A safety layer routes each action: auto, confirm, escalate, block. A reading model auto-executes 0% of unsafe actions vs a baseline's 38% (McNemar p<0.001). Plus a runtime loop: an agent earns or loses autonomy with each counterparty over time.

Curated research on AI agent social engineering, manipulated delegation, prompt injection, tool-use boundaries, and agent security evaluation.

Trusted financial AI, agentic workflows, and senior AI product/platform architecture.

A secure, extensible agent-runtime CLI for terminal workflows, with deterministic permissions, human approvals, file tools, shell execution, and durable sessions.

Agentic IT-ops assistant with a live tool-use trace panel - audits account hygiene and ticket SLA risk against synthetic or user-uploaded CSV data, built on the Claude API

Self-hosted AI gateway for Claude Code & Codex — route to DeepSeek, Qwen, Kimi, GLM, Gemini, Groq with your own API key. Up to 97% cheaper. 7-day free trial.

A layered Agent Harness framework — ReAct loop, tool registry, multi-provider LLM, workspace isolation. Pure Node.js.

Framework open source para evaluar agentes LLM con function calling / tool use. Scoring por dimensión (tool accuracy, response quality, safety) + CLI, API y dashboard.

A lightweight local Coding Agent harness inspired by learn-claude-code s20, featuring a minimal LLM tool-use loop, workspace-safe file access, command execution, and pytest-verified Phase 1 tools.

Benchmarking schema-valid false tool observations and defense baselines for tool-using LLM agents.

A controller that learns how a tool-using agent should spend compute at each step (WIDER, DEEPER, DECOMPOSE, STOP, or ESCALATE to a stronger model) and improves its own policy from logged traces. Judged on cost per solved task with paired statistics; ships trained policies and an offline embed API (pip install, no key needed).

AI tool use for Microsoft Office files

Open-source trust layer for autonomous AI — gate agent, robot, smart home, and industrial actions before they run. Policies, HITL, Ollama/OpenAI, audit. MIT. npm @sanctum-runtime/sdk