GITHUB TOPIC
11projects include this topic
The "guardrails" topic on GitHub groups 11 open-source projects in the DeepSeek Harness (DSH) ecosystem, led by dsh-memory with 308 GitHub stars. dsh-memory — White-box AGI architecture exploration: metacognition (self-awareness loop), continual learning (knowledge flywheel), world model (condition space + semantic spatiotemporal graph), self-improvement (bootstrapping discipline), zero-LLM white-box pipeline and auditable trust guardrails. Every project here is indexed by DSH Universe with live GitHub data — stars, activity and install status — so you can compare and install directly.
{count} projects
Exact GitHub Topic match
FuRongJun-1999
White-box AGI architecture exploration: metacognition (self-awareness loop), continual learning (knowledge flywheel), world model (condition space + semantic spatiotemporal graph), self-improvement (bootstrapping discipline), zero-LLM white-box pipeline and auditable trust guardrails.
fatmo666
Compiler-style pre-execution safety analysis for Harness shell actions.
AskTheWay
⚡ Millisecond System-1 judgement for every tool call in DeepSeek Harness — Jev-powered risk classification & evidence-gated auto-approval. Fail-closed by construction. dsh 生态第一个 System-1 决策插件
Asuna486-desuwa
Self-protection guardrails for the DeepSeek Harness: protected-path interception, backup-before-destroy, CLI self-recovery commands, and strict sandbox defaulting
couldbeme
Commitment write-gate for AI coding agents: two-tier pre-execution policy (deterministic guard + LLM judge) with measured receipts. DeepSeek Harness plugin, engine-agnostic core.
ishamishra0408
A teammate posts one Slack message. Your AI assistant reads it, believes it, and hands over your keys through a link preview — nothing shows in the channel. Three plugins for the dsh agent harness stop the message before it leaves. Live demo you can run: real detectors, a real model as the victim.
JW53222
Nine deterministic hooks that block a coding agent from weakening tests, swallowing errors, or stubbing type checks — each backed by a planted-failure test proving the guard can actually fire. Runs on Claude Code and DeepSeek Harness.
x7687315-gif
User-controlled policy and personalization runtime for DeepSeek Harness - enforce hard project constraints at the agent lifecycle boundary.
artemiroshnichenko
Production-ready plugins for DeepSeek Harness (DSH): remote SSH agent execution, integrated terminal & file tree, security guardrails, skills & MCP server console.
sashankh
Indirect prompt-injection guard for DeepSeek Harness: taints tool output by origin, gates privileged calls that follow untrusted content, and refuses credentials heading off the machine.
sperictao
DeepSeek Harness plugin: per-tool-call Auto-permission review powered by TypeSafe Jev, with account usage and API-key management inline on its settings page