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.

Observability for AI agents. See what your agent did, why it cost that much, and what to fix.

Extensible, low overhead Java Bytecode instrumentation agent for optimizing Java app performance

Persistent decision memory for AI agents: rationale, rejected approaches, and entity history. Connect any compatible agent through local MCP or the CLI.

The Audited Context Generation (ACG) Protocol prevents AI hallucinations with a dual-layer system. The UGVP layer links every fact to a precise source for verification. The RSVP layer audits the AI's logical reasoning when combining facts. This creates a fully transparent, machine-auditable trail for both source and logical integrity.

Local open-source dev tool to debug, secure, and evaluate LLM agents. Provides static analysis, dynamic security checks, and runtime monitoring - integrates with Cursor and Claude Code.

A curated list of research on LLM-agent traces: evidence tracing, execution provenance, failure attribution, observability, runtime safety, memory provenance, and learning from traces. Companion list of arXiv:2606.04990.

面向 DOCX 学术文档的可验证 AI Agent：规划、确定性执行、重读验证、Evidence 与 Human-in-the-loop。

Local-first trace recorder and searchable HTML viewer for AI agent runs.

🛠️ Enhance RAG systems with ACG to reduce hallucinations in LLM responses by improving accuracy and grounding in reliable external knowledge.

基于 Event 的 LLM-wiki 式 web 前后端 Coding Agent，有 trace 和 Eval 系统。

Local-first memory for coding agents: one complete record of every Claude Code, Codex and pi session, memories with evidence, nothing lost.

An MCP server for planning, execution and validation: Structured reasoning (think_*) + execution tracking (ship_*) + roadmap + signals for AI coding agents. Rust · stdio + Streamable HTTP · git-native, Agent-Trace-compatible traces.

Alibaba Java诊断利器Arthas

AI 审计网关与责任协议 — 一行 base_url 生成不可篡改的审计轨迹

Portable JSON for AI agent sessions. Spec 0.2.0. Converts Claude Code, Grok, Codex, Cursor, OpenCode, and Watchtower 5.x.

Know which AI agent wrote each line of your code, why, and what it cost — then undo just that agent's work.

Multi-agent platform for long-form synthesis. Controlled 6-agent sequential pipeline (Orchestration, Search, Writing, Style, Harmonization, Enforcing) with BM25 retrieval and a live Agent Trace UI. Runs end-to-end with zero API keys via a deterministic mock provider. Next.js 16, Prisma 7.

Cursor Agent TRACE, capture Cursor IDE agent sessions via hooks into signed AgentRust TRACE (Level 0) audit trails. Policy allow/deny, org collector to S3, and a local trail viewer for teams using Cursor AI agents.

View and debug coding agent transcripts — Claude Code, Codex, and more. Local-first, beautiful, searchable.