Entry
Appears in 11 awesome lists
by Continuum AI - Records a Claude Code run through a local proxy and replays it offline, reproducing it byte-for-byte with the network off, or forking it from any checkpoint onto a different model. Capture happens below the harness, so shell exit codes, per-turn file changes and MCP calls land on…
Section: Agent Infrastructure & Primitives · Records a coding agent at the process and socket boundary so model traffic, shell exit codes, per-turn file changes and MCP JSON-RPC share one timeline, then replays the run offline with the network off or forks it from a checkpoint onto a different model.
Section: Observability · by Continuum AI - Records a Claude Code run through a local proxy and replays it offline, reproducing it byte-for-byte with the network off, or forking it from any checkpoint onto a different model. Capture happens below the harness, so shell exit codes, per-turn file changes and MCP calls land on…
Section: Tools & Utilities · Standalone CLI that records model-provider traffic and replays a session offline with no provider contacted; DSH needs orca attach --port N because it resolves its provider origin from config rather than a base-URL environment variable.
Section: API tools · Records a coding-agent session below the harness, then replays it offline with the network off or forks it from any step onto a different model. Ships an MCP server. Apache-2.0.
Section: Toolkit for testing/debugging HTTP(S) and restAPI (RESTful) · Records the HTTP traffic of an AI coding agent and serves the recording back, so the same run re-executes with no model called, written in TypeScript
Section: 8. MLOps / LLMOps & Production · Records a coding-agent run below the harness and replays it offline with the network off, or forks it from a checkpoint onto another model.
Section: AI & LLM Testing · Records a coding-agent session below the harness, keeping the verbatim request and response bytes, then replays the same run offline with the network off or forks it from a checkpoint onto other models with a verify command deciding the verdict.
Section: On the radar · Record, replay, fork, and debug any agent run with any model; time travel for AI agents.
Section: September 13, 2026
Section: 링크 · 코딩 에이전트와 모델 제공자 사이의 HTTP 경계에서 실행 내용을 기록하고, 제공자 호출이나 API 키 없이 같은 실행을 다시 재생하는 오픈소스 CLI
Section: Development and Testing · Answer questions about past agent runs from their recordings
Databricks' open-source meta-harness (June 2026) that sits above Claude Code, Codex, Pi, and custom agents to compose, govern, and share live agent sessions from one control plane. The key harness insight is that enterprises don't need another agent framework — they need a portability and…
MIT-licensed TypeScript-native orchestration framework that plans multi-agent task DAGs at runtime, with approval gates, tracing, evaluation, checkpoints, and resumable execution in your own environment.
Workflow layer for OpenAI Codex CLI: stronger default sessions, reusable skills, native hooks, HUD/status surfaces, project guidance, and team-style execution commands.
Workflow engine for deterministic AI coding agents. Define development processes as YAML workflows (planning → implementation → validation → review → PR) with isolated Git worktrees for parallel execution. MIT licensed.
Local-first, model-agnostic environment for building, borrowing, and orchestrating specialist agents and teams across supported LLM hosts, with owner-scoped packages and host-enforced permissions. Apache 2.0 licensed.
Self-hosted Kubernetes-native sandbox runtime for AI coding agents (Claude Code, OpenHands, LangGraph). Same Sandbox CRD provisions a Pod + PVC + default-deny NetworkPolicy with optional gVisor isolation, hierarchical governance, and a streaming SSE invoke API.
Routes one coding thread across harnesses with quota-aware rotation between subscription profiles, Best-of-N runs, and cross-family review.
Hosted memory engine over MCP: decisions, preferences, and lessons follow an agent between sessions and tools, and recall re-ranks from reported outcomes rather than similarity alone. Remote endpoint with sign-in, or npx -y @mnemoverse/mcp-memory-server@latest with an API key. Claude Code, Cursor,…