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.
10 results
Local-first, self-hosted AI agent runtime with Claude Managed Agents-style APIs, sandboxed sessions, memory, tools, audit, replay, and a local Console.
Tensorlake sandbox execution providers for DeepSeek Harness
Privacy-minimal heuristic per-turn execution summaries for DeepSeek Harness
Observe-only hash-chained evidence receipts for DeepSeek Harness
Allow, ask, or deny DeepSeek Harness tool calls before execution
A safety harness plugin for DeepSeek Harness (DSH): protected-path enforcement, trash-based safe_delete with undo, last-known-good composition snapshots, pre-restart composition checks, and an audit journal.
DSH-Plugin: structural observability layer — real tool/skill usage recording (tools/result), skill-catalog audit, and a watchdog with health/error events. No model self-reporting.
DeepSeek Harness plugin: predict (pre-install) and detect (post-install) duplicate @deepseek-ai/dsh-* copies, version drift, and vendored core services to prevent Symbol-key crashes like "Cannot read properties of undefined (reading 'prepare')".
Enforce recycle-bin-only deletion on Windows: block del/rm/Remove-Item and other disk-erase commands, forbid automatically emptying the recycle bin, and stop + ask the user when the recycle bin or disk is full.
One-line DeepSeek Harness bundle that moves the execution world into a crash-resilient, heartbeat-kept, workspace-synced E2B sandbox.