a5c-ai

a5c-ai

Explained projects

docs: Babysitter: The Repo That Makes AI Agents Prove They’re Done
Workflow Automation
docs: Babysitter: The Repo That Makes AI Agents Prove They’re Done
Versioned workflows, quality gates, and deterministic loops turn AI coding from a conversation into a controlled system.
8 min read · Apr 8, 2026
a5c-ai/kanban: The Kanban Board That Treats Git Like a Database
Workflow Automation
a5c-ai/kanban: The Kanban Board That Treats Git Like a Database
Each card action becomes an append-only operation file. The board is rebuilt from Git history, so humans, terminals, web UI, and agents all share one deterministic source of truth.
8 min read · Apr 8, 2026
obedience-benchmark: The benchmark for when agents know the answer but ignore the instructions
Benchmarks & Eval
obedience-benchmark: The benchmark for when agents know the answer but ignore the instructions
a5c-ai/obedience-benchmark measures process fidelity, not just task completion, with Docker isolation, structured logs, and a judge that scores how closely an agent followed the script.
11 min read · Apr 8, 2026
cli: a5c-ai/claude-code-telegram-bot Turns Telegram Into a Remote Control Plane for Claude Code
AI Dev CLIs
cli: a5c-ai/claude-code-telegram-bot Turns Telegram Into a Remote Control Plane for Claude Code
A mobile wrapper, yes. More interestingly, a persistent session manager that keeps one Claude Code process alive, accepts voice and files, and lets you steer real coding work without sitting at the terminal.
8 min read · Apr 6, 2026
a5c-ai/.github: The Tiny Repo That Turns GitHub Into an AgentOps Funnel
Open-Source Replacements
a5c-ai/.github: The Tiny Repo That Turns GitHub Into an AgentOps Funnel
A profile repository that does almost no code work and a lot of strategic work: it frames Babysitter, routes visitors to the right next step, and turns an org page into a launch surface.
7 min read · Apr 6, 2026
The AI Operating System Hiding in a GitHub Template: Inside a5c-ai/seed-generic
Multi-Agent Frameworks
The AI Operating System Hiding in a GitHub Template: Inside a5c-ai/seed-generic
How a collection of hollow shell scripts and aggressive credential injection turns an empty repository into an autonomous, multi-agent development team.
7 min read · Apr 5, 2026
a5c-ai/generate-token-action and the Art of the Paranoiac CI Pipeline
Security & Supply Chain
a5c-ai/generate-token-action and the Art of the Paranoiac CI Pipeline
Why a specialized authentication tool abandoned the npm ecosystem to build a zero-dependency fortress in pure Node.js.
6 min read · Apr 4, 2026
babysitter-breakpoints: a5c-ai/babysitter: Putting AI Agents on a Leash
Agent Memory & Skills
babysitter-breakpoints: a5c-ai/babysitter: Putting AI Agents on a Leash
How a local-first middleware uses strict human breakpoints to turn unpredictable LLM execution into a deterministic state machine.
6 min read · Apr 4, 2026
Untethering the Terminal: Inside claude-code-telegram-bot
Coding Agents
Untethering the Terminal: Inside claude-code-telegram-bot
How a TypeScript daemon turns everyday messaging apps into a mobile-first control plane for autonomous coding agents.
7 min read · Mar 30, 2026
Babysitter: Putting a Hard-Coded Boss Inside the AI Agent
Multi-Agent Frameworks
Babysitter: Putting a Hard-Coded Boss Inside the AI Agent
How a5c-ai uses event-sourcing and "Quality Convergence" to turn flaky LLM coding into a deterministic engineering pipeline.
· Mar 26, 2026