managed-agents
Local-first, self-hosted AI agent runtime with Claude Managed Agents-style APIs, sandboxed sessions, memory, tools, audit, replay, and a local Console.
7 results
Local-first, self-hosted AI agent runtime with Claude Managed Agents-style APIs, sandboxed sessions, memory, tools, audit, replay, and a local Console.
Codex App Server model provider plugin for DeepSeek Harness
Durable long-horizon task runtime plugin for DeepSeek Harness
Runtime security guard for DeepSeek Harness (DSH) — blocks command injection, SSRF, credential exfiltration, and destructive operations at runtime.
A local-first developer control plane for multiple DeepSeek Harness runtimes.
AI Agent runtime authorization & evidence verification — tool-call GuardrailProvider, CCS 7-dimension verification standard, MCP/DSH security scanner, SSRF/command-injection/credential-exfil blocking with Ed25519 signed receipts.
Repository and agent-runtime analysis skills as an installable DeepSeek Harness plugin: repo recon, DSH enhancement analysis, runtime optimization, publish screening, and DSH plugin-potential assessment.