Code agents

A lightweight local workflow orchestrator for development and review agents.

A minimal, type-safe Python library for LLM chat completions with OpenAI, Azure OpenAI and Codex

Python library wrapping the Claude Code CLI: prompts, background agents, auth, MCP, plugins, and more

A minimal three-layer guardrails template for AI coding agents in Python projects.

编码 agent 框架:单 agent core + 扩展(MCP / 多 agent / web)

Intercept, inspect, and fix your RAG retrieval pipeline

Standalone, dependency-light tool implementations (calculator, file ops, datetime, unit conversion, JSON/CSV, text utilities) exposing OpenAI/Gemini-style function-calling schemas. No tool-calling execution loop - wire these into your own LLM tool-calling code, or into ragleap-agents when that ships. BYOK, no vendor lock-in.

Finds the coverage gates in your repo that can never fail a build (bundled Node.js runtime)

Persistent visual control sessions for external programming agents

Placeholder: name reserved by Google. This distribution contains no code.

Placeholder: name reserved by Google. This distribution contains no code.

Open-source SEO agent for link building. Plans campaigns and builds backlinks from Claude, Cursor or Codex via MCP. 1,141-site library.

A shared coordination board for AI coding agents driven by different people

Keep your agent skills deployed identically to Claude Code and Codex from one manifest, and audit projects so either agent sees the same instructions, skills and hooks.

Browser terminal deck: persistent named terminals, a Monaco file viewer, and automatic claude/codex session resume across restarts.

Autonomous terminal-based coding agent designed around verifiable software changes. Build. Verify. Ship.

A production-grade, terminal-based AI/Agentic coding harness with enhanced security

MCP server that lets any AI agent launch, watch and steer coding agents (Claude Code, Codex, Hermes, aider, ...) running in tmux panes.

Type-Safe Decoding for Autoregressive LLMs

vLLM-HUST plugin carriers for vllm-ascend: cascade two-stage decode, decode FIA de-mask, RoPE variant fixes, zero-cost wiring, MLP chunking (all default-off)

A least-privilege controller for local coding agents

Reusable multi-provider AI agents for web development across local projects

Wellmanifest unified standards runtime — policy-as-code checker for all wellmanifest standards

Workspace Intelligence Agent (WIA) — Graph-grounded workspace intelligence platform for code understanding, AST parsing, flow tracing, and RAG Q&A

Daily work log and token report across Claude Code accounts and devices, synced through your own private git repo

Verifiable execution receipts for Haystack agents. Every tool call mints a verifiable AER-1 receipt at zambo.dev.

Verifiable execution receipts for LlamaIndex agents. Every tool call mints a verifiable AER-1 receipt at zambo.dev.

Verifiable execution receipts for OpenAI Agents SDK agents. Every tool call mints a verifiable AER-1 receipt at zambo.dev.

Verifiable execution receipts for smolagents agents. Every tool call mints a verifiable AER-1 receipt at zambo.dev.