#agents

A drop-in engineering loop for coding agents: task contracts, verification reports, reviewer handoffs, and repo-level safety policies.

Universal control system for coding agents: shared memory, cross-project handoffs, research management, & MCP + Obsidian dashboards across products/repos.

No repository description published.

Deterministic iOS app validation CLI for AI coding agents.

Artificial Ecology For Thought and Emergent Reasoning. The Colony That Builds With You.

Safe Fastmail management tool for LLMs

Your engineering crew for Claude Code — 12 specialists plan, build, review and ship in any stack; the rules that matter are enforced, not remembered.

Open .skill Protocol - a sealed, inspectable package format for AI agent skills. Reference implementation: skillerr.

Governance CLI for AI-native software delivery and AI coding agents. Enforces traceability: ADR → REQ → ROADMAP → kanban. Native support for Codex, Claude Code, Gemini CLI, Cursor, Copilot, Windsurf, and Amazon Q.

Living memory for AI agents with an immune system. Episodes compress into identity. Zero dependencies, works with any client.

4-agent coding team dashboard — terminals, agent chat, GitHub board, Telegram bridge, and shared memory in one local web view.

MCP server that suggests repository-specific AI agent skills.

JupyDeep is an extension app for JupyterLab, your AI partner in Jupyter, powered by Pydantic AI/Agents — and beyond.

Portable agent messaging — findings, alerts, coordination.

Telegram MTProto CLI for scripts and agents, powered by mtcute.

Agents that plan, don't react. The model writes a typed plan once. The runtime runs it. Tool outputs never go back through the model — so your agent can't be prompt-injected through its tools, costs a fraction, and runs the same every time.

Typed capability graph (CGS), CML mappings, and path language for agents — 42 curated API catalogs

Unified server-side helper for the PocketShell Android and desktop clients — usage quotas, aplexer sessions, agent conversations, host setup. Published to PyPI as 'pocketshell'.

Senparc 全家桶的 AI 扩展包

Local cockpit for Claude Code CLI sessions — schedule routines, monitor token budget, manage long-running plans

One .stdai/ source of truth, fanned out to 22 AI coding tools: Claude Code, Codex, Cursor, Copilot, Gemini CLI, Windsurf/Devin, Amp, Warp and more. Native formats, Agent Skills, MCP, context budgets, drift detection.

Go utilities for Google ADK. It includes LLM clients, storage for sessions and memory, context compaction, artifacts and more!

Persistent structured memory for AI agent systems

No repository description published.

Chat with your LangGraph agent inside JupyterLab — a sidebar chat for any CompiledGraph

One gateway in front of every MCP server your agents can reach. A server that changes after you approved it is caught, the call is blocked before it runs, and nothing leaves your machine.

Orchestrate CLI coding agents (Claude Code, Codex) in tmux, each on its own git worktree and branch

No repository description published.

Enterprise-grade, open-source LangGraph Agent Server powered by PostgreSQL checkpoints & Redis distributed workers. Subagent traceability & SSE resilience.

AgoraHub: an agent-to-agent coordination hub. Named channels, per-channel shared state, an attention/obligation model, a verifiable transcript, message-driven triggering, and a git-friendly markdown mirror. Framework-agnostic (MCP + CLI + Python).