Agent Trace

AI coding agent with one Python core and three front-ends — headless CLI, Textual TUI, and an Electron desktop. Works with any OpenAI-compatible API, with risk-tiered permissions, event-sourced replayable sessions, and a fail-closed OS-level sandbox.

Local-first AI agent trace workbench. Inspect Claude Code, Codex and OTLP logs, compare runs, and export privacy-conscious reports. No backend or API keys.

Learn AI Engineering! Learn it. Build it. Ship it for others.

Autonomous coding workflow that generates implementations, runs unit test executions, and self-corrects runtime stack traces.

Privacy-first AI project and Skill feedback loop for Codex and Claude Code—turn corrections into traceable requirements and verified repair plans.

Observability and guardrails for your ai agents. AgentTrail Guard traces your agent's execution and automatically compiles repeat failures into permanent guardrails.

Curated list of AutoResearch use cases with optimization traces and open source implementations

A local-first AI desktop planning assistant that turns goals into executable time.

🤖 A full-stack Agent Chat Runtime for pre-production validation, built with act, TypeScript, and LangGraph JS combining streaming, multimodal, HITL, and tools with durable Task/Step execution, retry budgets, idempotency, compensation, distributed locks, context governance, OpenTelemetry tracing, model fallback, cost tracking, and Opik evaluation.

An agent skill for finding papers worth reading—trace research lineages, map evidence networks, and weigh supporting and conflicting findings to guide your next research decision.

Compile real-world Claude Code and Codex trajectories into verified, tradable post-training assets.

Agent Skill evaluation harness for paired variants, trace artifacts, and runner adapters

The living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor agents or humans in the loop, and turn completed work into reusable work experience and data to improve future agents.

Run a task with AI as a flow of steps you keep, reuse, and refine, not a one-off chat.

Evidence-chain whiteboard + MCP server for AI research agents: every claim traces back to the run and code that produced it. 讓 AI agent 做研究時，每個結論都能追到產生它的程式碼。Claude Code · Codex · Cursor · Gemini CLI

Understand Your Agents. Turn agent logs into interactive maps and stories. Explore decisions, replay the work, and get answers linked to the original evidence. For coding, research, and creative workflows.

🤖 A full-stack Agent Chat Runtime for pre-production validation, built with act, TypeScript, and LangGraph JS combining streaming, multimodal, HITL, and tools with durable Task/Step execution, retry budgets, idempotency, compensation, distributed locks, context governance, OpenTelemetry tracing, model fallback, cost tracking, and Opik evaluation.

Intercept and inspect Coding Agent API traffic from Claude Code, Codex CLI, Gemini CLI, Cursor CLI, OpenCode, Kimi/Kimi Code, Pi, and Hermes in a local trace viewer.

🎬 Evidence-led Seedance 2.5 / 2.0 prompt library: 840+ cases traced to original posts, 490+ cross-model retest runs, 27 copy-ready templates, 79 installable AI-video Skills. Synced daily from goodcase.ai. EN / 中文 / 日本語.

One person, one software company. Manage 47 AI agents from a single Electron app — with Harness Engineering (Skills + Hooks + FileWatchers) for disciplined, traceable AI workflows.

Resumable, traceable AI coding — plans and handoffs stay with the repo, across any host

Threat modeling for AI coding agents: point Claude Code, Codex or any agent at your repo and get an evidence-traced threat model. 36 architectures, 29 methods, MIT.

Runtime evidence that helps agents trace, profile, and burn down hotspots in application and native code, GPU kernels, and inference stacks.

The open-source AI research workbench for scientific research and agent workflows. Local-first, model-agnostic desktop app with extensible skills, MCP tools and connectors, Python/R execution and traceable artifacts for reproducible research on macOS, Windows and Linux.