Agentic Ledger: an open source flight recorder for AI agents (looking for testers and contributors) A developer has built Agentic Ledger, an open-source transparent proxy that records all LLM calls from AI agents without requiring code changes. The tool provides real cost accounting, loop detection, and budget enforcement, and is seeking testers and contributors. I have been building an open source tool called Agentic Ledger https://agentic-ledger.dev and it just reached the point where I need more eyes on it than my own. This post is an introduction and an ask. AI agents run unattended. They call LLMs in loops, use tools, spawn sub-agents, and spend real money, and most of that happens where you cannot see it. When an overnight coding loop burns $40 getting stuck on the same failing test, or a multi-agent crew quietly retries itself into a huge bill, you usually find out from the invoice. The observability tools that exist mostly want you to instrument your code with an SDK, and each one speaks one framework. I wanted the opposite: something that watches everything, requires changing nothing, and keeps the data on my machine. Agentic Ledger is a transparent proxy that sits between your agent and the LLM provider. You point your agent's base url at it, and it records every request and response, assigns each call an action id, works out what it cost, and passes the response through untouched. Your agent never knows it is there. php Your Agent - Agentic Ledger Proxy - OpenAI / Anthropic / any gateway | SQLite or Postgres | Live dashboard + API No SDK, no decorators, no monkey patching. It works with any framework and any provider because it operates at the only layer they all share: the HTTP call. Everything is local-first. Your prompts stay in a SQLite file on your machine or your own Postgres . MIT licensed. pip install -U agentic-ledger AGENTICLEDGER UPSTREAM URL=https://api.openai.com python -m agenticledger.proxy Or with Docker multi-arch, non-root, Sigstore-signed : docker run -p 8000:8000 \ -e AGENTICLEDGER UPSTREAM URL=https://api.openai.com \ -v $ pwd /data:/data \ ghcr.io/shekharbhardwaj/agentic-ledger:latest Then point your agent at it: client = OpenAI base url="http://localhost:8000/v1", default headers={"x-agenticledger-session-id": "run-1"}, For coding agents like Claude Code it is even less work, one env var and zero headers: export ANTHROPIC BASE URL=http://localhost:8000 claude The dashboard is at http://localhost:8000 . Real cost accounting. Per call, per session, per agent, per day, including prompt cache reads and writes priced with each provider's own convention. Cache traffic is where most of a coding agent's real spend lives, and most tools ignore it. My rule for this project: the numbers are meant to match your provider bill, and if they do not, that is a bug I want reported. Loop awareness. This is the part I have not seen anywhere else. The proxy infers agent loops from raw traffic: it stitches ReAct-style threads together, groups fresh-context iterations Ralph-style overnight loops into runs, and flags the pathologies that waste money, like the same tool called with the same arguments over and over, or a step budget blowing past its limit. In block mode it acts as a circuit breaker and returns HTTP 429 to a stuck loop instead of letting it burn. A loop runner. agenticledger run --max-iterations 50 --budget 25 --