ECC

ECC is an open-source agentic engineering toolkit that provides skills, hooks, and security for coding agents.

ECC is an operating layer and agentic engineering toolkit designed for coding agents like Claude Code, Codex, and Cursor. It provides a shared set of skills, hooks, Plan Canvas, unified memory, compute workflows, and AgentShield security across different tools. Users can install it natively or via managed adapters, connect repositories to turn project history into guidance, and inspect sessions using the local operator interface. The toolkit is MIT-licensed and open source, while the hosted GitHub App offers free, Pro, and Enterprise plans with private repository coverage and AgentShield security scans. It is used by engineering teams to keep models on track and manage agent workflows.

ECC at a glance

Best for: Software engineer
Runs on: Web, CLI, API, open source
Pricing: Free OSS plan; GitHub App Free plan; Pro plan with self-serve active-seat billing; Enterprise plan with custom rollout and support
Released: January 2026
Category: AI coding tool
Website: ecc.tools

Key features

Skills and hooks for coding agents
Plan Canvas for browser annotation
Unified memory for agent handoffs
AgentShield security and config scanner
Control Pane for session inspection
GitHub App repository analysis
Open-source local toolkit

Use it for

Reviewing code changes with a repeatable process
Checking security permissions and exposed secrets
Annotating and revising plans in the browser
Sharing project context between different agents

Alternatives to ECC

Agent Skills — Encodes senior-engineer workflows and quality gates into 24 skills.
Lcc — Cuts token counts significantly without losing exact session details.
claude-mem — It shares persistent, searchable agent memory across sessions and devices.
Context Engineering Kit — Improves agent reliability and code generation quality with minimal token footprint.
LangChain — Compose exactly the agent your use case needs from model, tools, prompt, and middleware.
OpenCode — Works with 75+ model providers, local models, and existing subscriptions
pstack — Improves AI coding agent outcomes with rigorous workflows.
Agent Archive — Hand off coding sessions between Claude Code, Codex, and Cursor across machines.
Oh My ClaudeCode — Orchestrates parallel Claude, Gemini, and Codex CLI workers.
AGENTS.md — It separates agent-specific instructions from human-focused README files.
Acyclic — Runs large tasks by splitting work across many parallel agents.
Agentic Bug Hunter — It drives the reconnaissance, triage and reporting loop an agent would run.

All ECC alternatives