Rerun

Dalaran is an Apache-2.0 robotics-focused observability and visualization stack for recording, replaying, and inspecting multimodal time-series data such as ROS 2 topics, LiDAR sweeps, camera streams, IMU readings, and TF transforms on a synchronized timeline. It is a hard fork of Rerun, uses an Arrow-backed columnar chunk store, renders synchronized 2D and 3D views, and exposes recorded data as dataframes for computation. The project supports Python, Rust, and C++ SDKs, a viewer and CLI, ROS 2 data, Rosbag 2 and MCAP replay, existing Rerun .rrd recordings, and Dalaran .dlr recording files with saved .dbl blueprints; recordings can be written to files or streamed to a viewer or remote catalog.

OrcaReplay is an open-source replay and debugging tool for AI-agent executions, built by the OrcaRouter.ai team. It records an agent run as a local trace, including model requests and responses, tool calls and results, shell exit codes and timing, filesystem snapshots, MCP traffic, and selected network activity. It runs as a local proxy and capture layer around an unmodified agent. A proxy records model traffic, while PATH shims, JSON-RPC interception, filesystem snapshots, fetch hooks, and optional TLS interception capture effects that model transcripts cannot show. The resulting timeline can be viewed, exported, queried through JSON or MCP, and analyzed with recorded versus inferred causal edges. The same recorded stream supports offline replay with the network blocked, forking from a derived checkpoint onto another model, and comparison of several models with an optional verification command. Replay uses the recorded conversation and workspace state; interactive terminal sessions can be approximate because prompts and interactive-only tools may not exist on the wire. The CLI is installed with npm, requires Node 20 or newer, stores runs under `.orca/runs/`, and the code, CLI, viewer, adapters, and trace format implementation are released under Apache-2.0; the trace specification is CC BY 4.0. Traces are local and redacted on write, but the project describes them as sensitive and treats redaction as best-effort.

ABot-Recon is a streaming 3D-reconstruction model and inference tool for reconstructing long video streams from video frames alone. At each step, it caches key-value features from the preceding 11 frames, predicts a point map in the current camera coordinate system, estimates the adjacent relative camera pose, and composes those poses sequentially into a global trajectory and point cloud without persistent learned long-range memory. It can output camera poses, relative poses, local and world point maps, colors, confidence maps, and run metadata. An optional loop-closure backend retrieves candidate revisited-frame pairs using DINOv2-SALAD descriptors, predicts relative-pose constraints with ABot-Recon, and refines the trajectory through sparse pose-graph optimization. The repository provides Python and command-line interfaces, a public model checkpoint, a demo, evaluation code, and visualization utilities. The released configuration targets Linux, Python 3.10 or later, PyTorch 2.5.1, and CUDA 12.1; source code is licensed under Apache License 2.0, while the model weights have separate terms in MODEL_LICENSE.md.

ROS 2 is an open-source robotics middleware (the successor to ROS/Robot Operating System) developed by Open Robotics and the ROS community that provides publish/subscribe topics, services, actions, parameters and lifecycle management for distributed robot software. It uses the DDS (Data Distribution Service) transport layer with implementations such as eProsima Fast DDS, Eclipse Cyclone DDS and RTI Connext, and includes client libraries (rclcpp, rclpy), tooling (colcon) and rosbag2 for logging and replay of topics. ROS 2 runs on Linux, Windows and macOS, integrates with simulators and robot stacks, and is distributed under the Apache 2.0 license.

UNREEL is a personal AI video streaming service that generates shows while they are watched instead of serving prerecorded episodes. A showrunner LLM writes shots incrementally, and MiniMax H3 Max Turbo renders them through fal; each story shot uses the previous shot’s last frame as its image-to-video input, preserving visual continuity as the stream advances. The player maintains a render buffer and swaps to the next clip when the current one ends, while captions display dialogue written verbatim by the showrunner. The application is built with Next.js, React, and TypeScript, and uses Nano Banana 2 for key art and Gemini 2.5 Flash through fal’s LLM router for the showrunner. It includes chained story films and hard-cut “chaos” channels, and requires a fal API key for generation.