GitHub Repository

A physics engine for agentic behavior. Sovereign-governed multi-agent dev substrate with hash-chained audit, RBAC FSM, atomic Git worktree orchestration, and Ed25519 identity. Not an agentic wrapper — an agentic OS.

9 starsGo

Castra – Strip orchestration rights from your LLMs

Name: Castra – Strip orchestration rights from your LLMs
Availability: InStock
Author: amangsingh

by amangsingh·Apr 1, 2026·8 points·9 comments

Visit Project View on HN

AI Analysis

●●●BangerBig BrainWizardry

Cryptographic audit chain and DB-as-truth architecture for multi-agent systems.

Strengths

•SHA-256 hash-linked ledger with Ed25519 signatures makes audit trails cryptographically verifiable
•Dual-gate approval requires sequential QA then Security signoff—no self-approving code possible
•Custom SQLite VFS with AES-256-CTR encryption means database is unreadable without device key

Weaknesses

•Zero forks or stars suggests untested in production despite bold claims
•Agent orchestration space is crowded—needs proof this beats existing frameworks

Post Description

I got tired of AI agents forgetting what they were doing the moment their context window filled. The current industry solution is to write massively bloated agent harnesses full of defensive spaghetti just to stop models from drifting.

The problem is treating chat history as project state. A conversation is not a ledger.

Castra is a compiled Go binary that strips orchestration rights from the LLM. State lives in an encrypted, local SQLite database (castra.db). The LLM is just a stateless executor — it reads the DB, executes a highly constrained task, and the result is written back subject to rigid state-machine rules.

What it actually does: - 7-Role RBAC: Hard jurisdictional boundaries (Architect plans, Engineer builds, QA tests). - Dual-Gate Approval: A task cannot reach done without explicit, sequential approval from both a QA agent and a Security agent. No self-approving code. - Cryptographic Audit Chain: Every action is logged into a SHA-256 hash-linked, Ed25519-signed ledger. - Multi-Vendor: Works with Claude, Copilot, Gemini, etc. via a standard AGENTS.md protocol. Anything that supports AGENTS.md and can run terminal commands.

Proof of Work: I built this by hand up to v1.3.0. Then, I turned Castra on itself. The agents governed by this exact CLI took over and built the architecture up to v3.1.2—including the cryptographic log chain itself. The proof is in castra-log.jsonl in the repo.

If you are running multi-agent workflows and hitting the context amnesia wall, stop trying to prompt-engineer your way out of it. Fix the state machine.