Reference architecture for fail-open, witness-only evidence systems with independent verification and public settlement.
GitHub repository with 5 stars and 1 forks.
Topics: agent-observability, audit-trails, cryptographic-attestation, distributed-logging, edge-systems, fail-open, non-repudiation, observability, tamper-evident, verifiable-logs
Trending score 0.02, activity score 0.00, stars gained +0, forks gained +0.
2026-06-05: 5 stars and 1 forks.
Agent-native LLM router that optimizes your agent with every run. Zero harness changes — every model call reliable, traceable, secure, and cost-effective.
GitHub repository with 140 stars and 3 forks.
Trending score: 2.46; stars gained: +43; forks gained: +2.
Language: Rust
Topics: acp, agent-guardrails, agent-harness, agent-observability, ai-agent, ai-agents
Intercept and inspect Coding Agent API traffic from Claude Code, Codex CLI, Gemini CLI, Cursor CLI, OpenCode, Kimi, Pi, and Hermes in a local trace viewer.
GitHub repository with 1,431 stars and 155 forks.
Trending score: 2.07; stars gained: +154; forks gained: +21.
Language: Python
Topics: agent-debugging, agent-observability, ai-agents, ai-tools, api-debugging, claude-code
TraceRoot - open-source observability and self-healing layer for AI agents. YC S25
GitHub repository with 604 stars and 150 forks.
Trending score: 1.19; stars gained: +2; forks gained: +0.
Language: TypeScript
Topics: agent-observability, agentic, ai-observability, analytics, debugging-tool, developer-tools
open source agent engineering platform: traces, evals, and metrics to debug and improve your AI agents. Integrates with LangGraph, CrewAI, Claude Agent SDK, and more.
GitHub repository with 263 stars and 17 forks.
Trending score: 0.88; stars gained: +7; forks gained: +1.
Language: Python
Topics: agent-engineering, agent-evaluation, agent-observability, agentic-ai, claude-agent-sdk, crewai
An open-source terminal coding agent runtime and CLI for real project work.
GitHub repository with 14 stars and 1 forks.
Trending score: 0.52; stars gained: +1; forks gained: +0.
Language: TypeScript
Topics: agent-framework, agent-memory, agent-observability, agent-runtime, agentic-coding, autonomous-agent
Local execution trees for TypeScript AI agents. agent-inspect helps you understand what happened inside an AI agent run — locally. It turns manual steps, tool calls, LLM calls, structured logs, failures, durations, and run metadata into readable execution trees you can inspect from the terminal. It is built for TypeScript/Node.js developers..
GitHub repository with 34 stars and 18 forks.
Trending score: 0.49; stars gained: +2; forks gained: +1.
Language: TypeScript
Topics: agent-observability, agentic-ai, ai, ai-agent, ai-debugging, ai-logging-library
Agent-native LLM router that optimizes your agent with every run. Zero harness changes — every model call reliable, traceable, secure, and cost-effective.
GitHub repository with 140 stars and 3 forks.
Trending score: 2.46; stars gained: +43; forks gained: +2.
Language: Rust
Topics: acp, agent-guardrails, agent-harness, agent-observability, ai-agent, ai-agents
Intercept and inspect Coding Agent API traffic from Claude Code, Codex CLI, Gemini CLI, Cursor CLI, OpenCode, Kimi, Pi, and Hermes in a local trace viewer.
GitHub repository with 1,431 stars and 155 forks.
Trending score: 2.07; stars gained: +154; forks gained: +21.
Language: Python
Topics: agent-debugging, agent-observability, ai-agents, ai-tools, api-debugging, claude-code
TraceRoot - open-source observability and self-healing layer for AI agents. YC S25
GitHub repository with 604 stars and 150 forks.
Trending score: 1.19; stars gained: +2; forks gained: +0.
Language: TypeScript
Topics: agent-observability, agentic, ai-observability, analytics, debugging-tool, developer-tools
open source agent engineering platform: traces, evals, and metrics to debug and improve your AI agents. Integrates with LangGraph, CrewAI, Claude Agent SDK, and more.
GitHub repository with 263 stars and 17 forks.
Trending score: 0.88; stars gained: +7; forks gained: +1.
Language: Python
Topics: agent-engineering, agent-evaluation, agent-observability, agentic-ai, claude-agent-sdk, crewai
An open-source terminal coding agent runtime and CLI for real project work.
GitHub repository with 14 stars and 1 forks.
Trending score: 0.52; stars gained: +1; forks gained: +0.
Language: TypeScript
Topics: agent-framework, agent-memory, agent-observability, agent-runtime, agentic-coding, autonomous-agent
Local execution trees for TypeScript AI agents. agent-inspect helps you understand what happened inside an AI agent run — locally. It turns manual steps, tool calls, LLM calls, structured logs, failures, durations, and run metadata into readable execution trees you can inspect from the terminal. It is built for TypeScript/Node.js developers..
GitHub repository with 34 stars and 18 forks.
Trending score: 0.49; stars gained: +2; forks gained: +1.
Language: TypeScript
Topics: agent-observability, agentic-ai, ai, ai-agent, ai-debugging, ai-logging-library