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.
23 results
Local-first, self-hosted AI agent runtime with Claude Managed Agents-style APIs, sandboxed sessions, memory, tools, audit, replay, and a local Console.
DSH redteam security research modes and runtime plugins, managed from one settings page: deploy the nine presets, install, update and uninstall the seventeen runtime plugins for the current profile.
Security audit plugin for DeepSeek Harness: static permission profiling and a runtime sentinel for third-party plugins
Correctover runtime security for DeepSeek Harness (DSH): CCS 7-dimension verification, command-injection/SSRF/credential-exfil blocking, Ed25519 receipts, audit-first. Install with `dsh plugin add dsh-correctover`.
Discovery + management wrappers around the gh CLI for AI coding agents. Ships as a standard agent skill, an Agent Plugins 1.0 plugin (plugin.json + skills/), and a dsh plugin (dsh.bundle.patch registers the skill at runtime).
Audit deepseek-harness (DSH) plugins before install, guard them at runtime. Static verdict + pre-install audit protocol; supply-chain checks (typosquat, OSV); exfiltration & ransomware detection, honeypot canaries, integrity baseline. Alarm-only; blocks confirmed destructive ops.
Static DSH plugin compatibility audit before installation, plus bounded Loader lifecycle observation
Disk-usage audit for DeepSeek Harness (dsh) data directories: total size, per-directory breakdown, largest files, and oversized-file warnings (session logs can hit hundreds of MB). Zero runtime dependencies, read-only. CLI + agent-callable disk_audit tool.
Scan agent skill packages for static security risks. Use for skill audit, security check, prompt-injection review, suspicious scripts, unsafe dependencies, zip package review, and pre-install skill review. Not for runtime monitoring.
Security for DeepSeek Harness in two layers: source-backed pre-install vetting plus fail-closed runtime guardrails and HMAC-chained audit logs. Zero runtime dependencies.
Security review gate for DeepSeek Harness (dsh) plugins: static pre-install vetting of malicious code, vulnerabilities and supply-chain risks (with deobfuscation decoding), runtime audit, optional tool-call guard, and a one-click web review/install/uninstall panel.
A runtime prompt-injection shield for DeepSeek Harness tool results.
Runtime security guard for DeepSeek Harness (DSH) — blocks command injection, SSRF, credential exfiltration, and destructive operations at runtime.
Fail-closed MCP tool baseline and runtime approval security for DeepSeek Harness.
Config drift detective for DSH: snapshots profile/plugin state on startup, records diffs, exposes a read-only history tool. Zero runtime deps, no custom events.
Make Git Bash the only terminal tool for DeepSeek Harness on Windows: enables the bash executor and tool on win32, disables PowerShell (pwsh) everywhere, ships standard-bash/code-bash/cordis-bash agent presets, and sets the sandbox/approval defaults Git Bash's cygwin runtime needs.
Plug/unplug any DeepSeek Harness plugin cleanly: list every mounted layer, disable/enable without deleting, remove bundles + patch rows + dependencies in one pass, and audit for orphaned/dangling plugin state. Zero runtime dependencies; read-only by defau
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.
Container-isolated backend for the DeepSeek Harness code-execution seam: Code Mode programs run in a fresh container with no network, a read-only rootfs, and kernel-enforced memory, CPU, and pid ceilings
Evidence-backed runtime nutrition labels for DeepSeek Harness plugins and tool namespaces
Natural-language driven dynamic assembler for DeepSeek Harness (dsh): discovers plugins at runtime (official-first, third-party optional), generates assembly plans, and loads them via Cordis — with built-in security audit gates for unofficial plugins.
Runtime data-flow audit log for DeepSeek Harness: who mutated what, in what order — per-plugin, per-fiber attribution.
Local tool-call failsafe and DWGR-8 personal governance proxy gate for DSH: blocks high-risk shell patterns, credential leaks, and enforces declarative param-level boundaries with hash-linked JSONL audit logs and optional Gateway.