Agentic Ledger

Runtime observability for AI agents — see exactly what your agent did, why it did it, and what it cost.

Website: agentic-ledger.dev

The numbers are meant to match your provider bill. If they don't, that's a bug we want.

Works with any agent framework, any LLM provider, any model gateway. Zero code changes required. Point your agent at the proxy and everything is captured automatically.

How it works

Agentic Ledger runs as a transparent proxy between your agent and the LLM provider. It intercepts every request and response, assigns it an action_id, stores it, and returns the upstream response unmodified. Your agent never knows the proxy is there.

Your Agent  →  Agentic Ledger Proxy  →  OpenAI / Anthropic / LiteLLM / any LLM
                      ↓
               SQLite or Postgres
                      ↓
               Live Dashboard + API

Quick Start

Step 1 — Start the proxy

With Docker (recommended, no Python required):

docker run -p 8000:8000 \
  -e AGENTLEDGER_UPSTREAM_URL=https://api.openai.com \
  -v $(pwd)/data:/data \
  ghcr.io/shekharbhardwaj/agentic-ledger:latest

The image is multi-arch (amd64/arm64), runs as a non-root user, and every release is signed with Sigstore and ships an SBOM. Hardening a shared deployment (TLS, auth keys, redaction, verification)? See the deployment guide.

Or with docker compose (SQLite by default — see docker-compose.yml):

AGENTLEDGER_UPSTREAM_URL=https://api.openai.com docker compose up

With uv:

uv add agentic-ledger
AGENTLEDGER_UPSTREAM_URL=https://api.openai.com uv run python -m agentledger.proxy

With pip:

python -m venv venv && source venv/bin/activate
pip install agentic-ledger
AGENTLEDGER_UPSTREAM_URL=https://api.openai.com ./venv/bin/python -m agentledger.proxy

Postgres? Install the extra and set AGENTLEDGER_DSN:

bash

pip install "agentic-ledger[postgres]"
AGENTLEDGER_DSN=postgresql://user:password@localhost/agentledger

Note: the Docker image uses SQLite only. For Postgres with Docker, install via pip instead.

OpenTelemetry? Install the extra and set AGENTLEDGER_OTEL_ENDPOINT:

bash

pip install "agentic-ledger[otel]"
AGENTLEDGER_OTEL_ENDPOINT=http://localhost:4318

Proxy starts on http://localhost:8000. Traces are saved to agentledger.db in the current folder (or /data/agentledger.db in Docker).

Step 2 — Point your agent at the proxy

Two changes: set base_url to the proxy and add a session ID header to group calls into a run. Everything else — your API key, model, messages — stays exactly the same.

OpenAI:

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:8000/v1",  # ← proxy
    api_key="your-openai-key",
    default_headers={"x-agentledger-session-id": "run-1"},
)

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Research the top 3 AI trends in 2026"}],
)

Anthropic:

import anthropic

client = anthropic.Anthropic(
    base_url="http://localhost:8000",  # ← proxy
    api_key="your-anthropic-key",
    default_headers={"x-agentledger-session-id": "run-1"},
)

LiteLLM / OpenRouter / any gateway:

# Point Agentic Ledger at your gateway
AGENTLEDGER_UPSTREAM_URL=http://localhost:4000 uv run python -m agentledger.proxy

# Then point your agent at Agentic Ledger
client = OpenAI(base_url="http://localhost:8000/v1", ...)

Step 3 — Open the dashboard

http://localhost:8000

The web app updates live via WebSocket as calls come in. No refresh needed.

• Loop Lens — every loop run with status (running / flagged / complete), a cost-per-iteration chart, per-iteration breakdowns, and plain-English explanations of every flag
• Sessions — every session with three views: expandable call cards (response, thinking, tool calls, cache tokens, interaction badges), a Flow DAG of agent handoffs, and a Trace waterfall with real parent links from the loop engine
• Search — full-text across prompts, outputs, and agents

The classic single-file dashboard remains at http://localhost:8000/classic:

• Calls tab — every LLM call with full prompt, system prompt, tool calls, tool results, output, tokens, cost, latency, and errors
• Flow tab — visual DAG of your multi-agent system. Each agent is a node with aggregated cost, latency, and call count. Edges represent handoffs. Click a node to highlight its calls.
• Trace tab — Gantt/waterfall timeline showing every call as a horizontal bar on a shared time axis. Parallel calls appear side-by-side at the same position — no instrumentation required. Works purely from timestamps. Click any bar to jump to the full call detail. Budget warnings show as an amber border on the bar without hiding the agent colour.
• Search — full-text search across all sessions by prompt, output, agent name, or user ID

Coding agents — Claude Code, Ralph loops & friends

Claude Code (and most coding agents) can be pointed at the proxy with a single environment variable — no headers, no code changes:

AGENTLEDGER_UPSTREAM_URL=https://api.anthropic.com uv run python -m agentledger.proxy

export ANTHROPIC_BASE_URL=http://localhost:8000
claude

Agentic Ledger fingerprints Claude Code traffic automatically: every call is tagged framework=claude-code, and instead of one undifferentiated bucket, each Claude Code session appears under its real session UUID (the same id claude --resume shows), with prompt-cache reads/writes captured and priced correctly — cache traffic is where most of a coding agent's real spend lives.

Running an overnight loop (Ralph-style while :; do cat PROMPT.md | claude -p; done)? Use the built-in loop runner — it re-executes your command each iteration, attributes every call to the run (via the base URL, no headers needed), and stops on a completion promise, a budget ceiling, or the iteration cap:

AGENTLEDGER_UPSTREAM_URL=https://api.anthropic.com \
AGENTLEDGER_COMPLETION_PROMISE="ALL TASKS COMPLETE" \
uv run python -m agentledger.proxy

agentledger run --max-iterations 50 --budget 25 -- \
  claude -p "$(cat PROMPT.md)" --dangerously-skip-permissions

Each iteration shows up as iteration N of the run in /api/runs; when the agent prints the completion promise in a response, run status flips to complete and the loop exits with a cost/token summary. Any existing loop script works too — poll GET /api/runs/{run_id} yourself, or let the proxy's budgets (AGENTLEDGER_BUDGET_DAILY=25.00) hard-stop a runaway loop.

The same recipe works for any client with a base-URL override (Codex CLI, opencode, OpenClaw, LiteLLM-based stacks) — set the OpenAI/Anthropic base URL to the proxy and traffic is captured; add x-agentledger-* headers when you want explicit attribution.

OTel-native tools (Gemini CLI, Codex [otel], AutoGen/AG2, Pydantic AI, Vercel AI SDK) don't need the proxy at all — point their OTLP exporter at the ledger and GenAI spans are ingested directly:

export OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:8000
export OTEL_EXPORTER_OTLP_PROTOCOL=http/json

Framework guides — one per integration in docs/integrations: Claude Code, Codex CLI, opencode, OpenClaw, BMAD-METHOD, LangGraph/LangChain, CrewAI, OpenAI Agents SDK, Gemini CLI, AutoGen/AG2, Pydantic AI, Vercel AI SDK, LiteLLM, and OpenRouter.

Production deployment — TLS termination, auth keys, redaction, image signature/SBOM verification, enterprise mirrors, and scaling guidance in docs/deployment.md.

What gets captured

Every LLM call is stored with:

API reference

Examples:

# All calls in a session
curl http://localhost:8000/session/run-1

# Search across all sessions
curl "http://localhost:8000/api/search?q=failed+to+connect"

# Download JSON audit trail (includes an integrity tag; keyed HMAC when configured)
curl http://localhost:8000/export/run-1 -o audit-run-1.json

# Printable HTML report — open in browser, print to PDF
open http://localhost:8000/export/run-1/report

MCP server

Agentic Ledger exposes its captured data as an MCP (Model Context Protocol) tool server at POST /mcp. Point Claude Desktop, Cursor, or any MCP-compatible client at it to query traces directly from your AI assistant.

Tools available:

Configure in claude_desktop_config.json (HTTP, against a running proxy):

{
  "mcpServers": {
    "agentledger": {
      "url": "http://localhost:8000/mcp"
    }
  }
}

Or as a stdio subprocess — for clients that launch servers as commands (no running proxy required; reads the same database):

{
  "mcpServers": {
    "agentledger": {
      "command": "agentledger",
      "args": ["mcp"],
      "env": { "AGENTLEDGER_DSN": "sqlite:////absolute/path/to/agentledger.db" }
    }
  }
}

If AGENTLEDGER_API_KEY is set, pass it as a header:

{
  "mcpServers": {
    "agentledger": {
      "url": "http://localhost:8000/mcp",
      "headers": { "x-agentledger-api-key": "your-key" }
    }
  }
}

Once connected, you can ask your assistant things like:

• "What did the SearchAgent do in the last session?"
• "Show me all calls that mentioned rate limit errors"
• "What was the total cost of session run-abc123?"

Configuration

Environment variables

Core:

Cost budgets — block calls that exceed a spend limit (returns HTTP 429):

Rate limits — block calls that exceed request frequency (returns HTTP 429, sliding 60-second window):

Loop engine — every call is stitched into ReAct threads (thread_id, step_index, prev_action_id) and fresh-context loop iterations are grouped into runs, with stuck-loop detection:

Alerts — POST to your webhook when a threshold is breached (does not block calls — see Alerts):

OpenTelemetry — emit spans to any OTLP-compatible collector (requires pip install "agentic-ledger[otel]" — see OpenTelemetry export):

Pricing overrides — override or extend the built-in per-token pricing table (merged at startup):

Common startup examples

# Local dev — OpenAI (default)
AGENTLEDGER_UPSTREAM_URL=https://api.openai.com uv run python -m agentledger.proxy

# Local dev — Anthropic
AGENTLEDGER_UPSTREAM_URL=https://api.anthropic.com uv run python -m agentledger.proxy

# Local dev — LiteLLM gateway (any model)
AGENTLEDGER_UPSTREAM_URL=http://localhost:4000 uv run python -m agentledger.proxy

# Production — Postgres + auth + budgets + rate limits + alerts
AGENTLEDGER_UPSTREAM_URL=https://api.openai.com \
AGENTLEDGER_DSN=postgresql://user:password@localhost/agentledger \
AGENTLEDGER_API_KEY=my-secret \
AGENTLEDGER_BUDGET_DAILY=20.00 \
AGENTLEDGER_BUDGET_SESSION=2.00 \
AGENTLEDGER_RATE_LIMIT_SESSION_RPM=20 \
AGENTLEDGER_RATE_LIMIT_USER_RPM=60 \
AGENTLEDGER_ALERT_WEBHOOK_URL=https://hooks.slack.com/services/xxx/yyy/zzz \
AGENTLEDGER_ALERT_COST_PER_CALL=0.50 \
AGENTLEDGER_ALERT_DAILY_SPEND=15.00 \
uv run python -m agentledger.proxy

When AGENTLEDGER_API_KEY is set, pass it to access protected endpoints:

# Header
curl -H "x-agentledger-api-key: my-secret" http://localhost:8000/session/run-1

# Query param (browser)
http://localhost:8000?api_key=my-secret

Scoped API tokens (RBAC)

The master key is convenient but coarse. For team access, mint scoped, revocable tokens with roles instead of sharing the master secret. Tokens are random secrets shown once at creation; only their SHA-256 hash is stored.

Roles are hierarchical:

# Mint a viewer token (admin only — use the master key to bootstrap)
curl -X POST http://localhost:8000/api/tokens \
  -H "x-agentledger-api-key: my-secret" \
  -H "content-type: application/json" \
  -d '{"name": "grafana-readonly", "role": "viewer", "expires_in_days": 90}'
# → {"token_id": "...", "token": "agl_…", "role": "viewer", ...}  (token shown once)

# Use it (Bearer header, x-agentledger-token, or ?token=)
curl -H "Authorization: Bearer agl_…" http://localhost:8000/api/sessions

# List and revoke
curl -H "x-agentledger-api-key: my-secret" http://localhost:8000/api/tokens
curl -X DELETE -H "x-agentledger-api-key: my-secret" http://localhost:8000/api/tokens/<token_id>

Auth is enforced only when AGENTLEDGER_API_KEY is set; the master key is the admin bootstrap for minting tokens. The live /ws feed accepts the same credentials (?api_key=, ?token=, Authorization: Bearer, or x-agentledger-token) and rejects unauthenticated connects with close code 1008 — the dashboard forwards its page credential to the socket automatically.

Request headers

Pass these from your agent on each LLM call. All optional. They enrich captured data, power the Flow tab, and enable per-dimension budgets and rate limits.

Single agent — fully annotated:

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:8000/v1",
    api_key="your-openai-key",
    default_headers={
        "x-agentledger-session-id":  "run-abc123",
        "x-agentledger-user-id":     "user-42",
        "x-agentledger-agent-name":  "researcher",
        "x-agentledger-app-id":      "my-app",
        "x-agentledger-environment": "production",
    },
)

Multi-agent system — tracking handoffs:

from openai import OpenAI

# Orchestrator
orchestrator_client = OpenAI(
    base_url="http://localhost:8000/v1",
    api_key="your-openai-key",
    default_headers={
        "x-agentledger-session-id":  "run-abc123",
        "x-agentledger-agent-name":  "orchestrator",
    },
)

# Researcher (receives handoff from orchestrator)
researcher_client = OpenAI(
    base_url="http://localhost:8000/v1",
    api_key="your-openai-key",
    default_headers={
        "x-agentledger-session-id":   "run-abc123",
        "x-agentledger-agent-name":   "researcher",
        "x-agentledger-handoff-from": "orchestrator",
        "x-agentledger-handoff-to":   "researcher",
    },
)

The Flow tab renders orchestrator → researcher as a DAG with cost and latency on each node.

OpenAI Agents SDK (openai-agents) — per-agent clients:

The openai-agents SDK uses its own internal OpenAI client. To pass Agentic Ledger headers you need to create a client per agent using OpenAIResponsesModel and set it as the agent's model.

import uuid
import os
from openai import AsyncOpenAI
from agents import Agent
from agents.models.openai_responses import OpenAIResponsesModel

SESSION_ID = f"run-{uuid.uuid4().hex[:8]}"  # one per execution
BASE_URL = os.getenv("OPENAI_BASE_URL")      # e.g. http://localhost:8000/v1

def al_model(agent_name: str, model: str = "gpt-4o-mini",
             handoff_from: str | None = None, handoff_to: str | None = None):
    """Create a model instance that sends Agentic Ledger metadata headers."""
    if not BASE_URL:
        return model  # proxy not configured — use default client
    headers = {
        "x-agentledger-session-id": SESSION_ID,
        "x-agentledger-agent-name": agent_name,
    }
    if handoff_from:
        headers["x-agentledger-handoff-from"] = handoff_from
    if handoff_to:
        headers["x-agentledger-handoff-to"] = handoff_to
    client = AsyncOpenAI(base_url=BASE_URL, api_key=os.getenv("OPENAI_API_KEY", ""),
                         default_headers=headers)
    return OpenAIResponsesModel(model=model, openai_client=client)

planner = Agent(name="PlannerAgent", model=al_model("PlannerAgent", handoff_to="SearchAgent"), ...)
searcher = Agent(name="SearchAgent",  model=al_model("SearchAgent",  handoff_from="PlannerAgent", handoff_to="WriterAgent"), ...)
writer   = Agent(name="WriterAgent",  model=al_model("WriterAgent",  handoff_from="SearchAgent",  handoff_to="EmailAgent"), ...)
emailer  = Agent(name="EmailAgent",   model=al_model("EmailAgent",   handoff_from="WriterAgent"), ...)

Each agent's calls are tagged with its name and pipeline position. The Flow tab renders the full PlannerAgent → SearchAgent → WriterAgent → EmailAgent DAG automatically.

Why per-agent clients? set_default_openai_client() sets a single global client — fine for single-agent apps, but it can't carry different agent_name or handoff_* headers per agent in a multi-agent system. Per-agent OpenAIResponsesModel instances are the correct approach.

Alerts

Agentic Ledger fires a POST to your webhook URL when a threshold is breached. You connect it to whatever you already use — Slack, PagerDuty, Discord, email, or a custom endpoint. Agentic Ledger sends the payload; the integration is on your side.

Payload format:

{
  "type":       "high_cost",
  "message":    "Single call cost $0.1842 exceeded threshold $0.10",
  "value":      0.1842,
  "threshold":  0.10,
  "action_id":  "a1b2c3d4-...",
  "session_id": "run-1",
  "agent_name": "researcher",
  "timestamp":  "2026-04-03T12:00:00+00:00"
}

Alert types:

Budgets vs alerts:

• Budgets (AGENTLEDGER_BUDGET_*) — block the call before it reaches the LLM. Agent gets HTTP 429.
• Alerts (AGENTLEDGER_ALERT_*) — the call goes through, you get notified after.

Slack — create an Incoming Webhook and point AGENTLEDGER_ALERT_WEBHOOK_URL at it.

PagerDuty — use the Events API v2 URL or a thin adapter that maps type → PagerDuty severity.

Discord — use a Discord channel webhook URL directly.

Custom — any HTTP endpoint that accepts a JSON POST.

OpenTelemetry export

Agentic Ledger can emit every intercepted LLM call as an OTel span to any OTLP-compatible collector: Grafana Tempo, Jaeger, Honeycomb, Datadog, Dynatrace, or any vendor that supports OTLP/HTTP.

Install the extra (Docker image includes OTel — no extra step needed when using Docker):

pip install "agentic-ledger[otel]"
# or
uv add "agentic-ledger[otel]"

Configure:

Example — Grafana Tempo:

AGENTLEDGER_UPSTREAM_URL=https://api.openai.com \
AGENTLEDGER_OTEL_ENDPOINT=http://localhost:4318 \
AGENTLEDGER_OTEL_SERVICE_NAME=my-agent \
uv run python -m agentledger.proxy

Example — Honeycomb:

AGENTLEDGER_OTEL_ENDPOINT=https://api.honeycomb.io \
AGENTLEDGER_OTEL_HEADERS=x-honeycomb-team=YOUR_API_KEY,x-honeycomb-dataset=llm-traces \
uv run python -m agentledger.proxy

Span attributes emitted (GenAI semantic conventions):

Spans are grouped into traces by session_id — all calls in a session appear as one trace in your backend. Parent-child relationships follow x-agentledger-parent-action-id. Error spans (status_code != 200) are marked with StatusCode.ERROR.

Compliance export

Every session can be exported as an integrity-tagged audit trail — useful for regulated industries, internal audits, or passing traces to external tools.

# Machine-readable JSON with an integrity tag over the calls array
curl http://localhost:8000/export/run-1 -o audit-run-1.json

# Printable HTML — open in browser and print to PDF
open http://localhost:8000/export/run-1/report

The JSON export carries an integrity tag over the calls array. By default this is a sha256 checksum — it catches accidental corruption but is not a signature (anyone who edits the calls can recompute it). Set AGENTLEDGER_EXPORT_HMAC_KEY to switch to a keyed hmac-sha256 tag, which is tamper-evident: a recipient holding the key can detect any modification, and the tag cannot be forged without the key.

Releasing

Tagging a version triggers the full release pipeline automatically:

git tag v0.2.0
git push origin v0.2.0

This runs three jobs:

1. Docker — builds ghcr.io/shekharbhardwaj/agentic-ledger:{version} and :latest for linux/amd64 + linux/arm64, pushes with SBOM + provenance attestations, signs the digest with Sigstore cosign (keyless), and mirrors to Docker Hub when the DOCKERHUB_USERNAME/DOCKERHUB_TOKEN secrets are configured
2. PyPI — builds and publishes agentic-ledger=={version} to PyPI using trusted publishing (no API token needed), with PEP 740 attestations
3. GitHub Release — creates a release with auto-generated changelog and attaches the image SBOM (SPDX)

First-time PyPI setup (one time only):

1. Go to pypi.org/manage/account/publishing
2. Add a new pending publisher:
   code

   PyPI project name:  agentic-ledger
   Owner:              ShekharBhardwaj
   Repository:         AgenticLedger
   Workflow name:      release.yml
   Environment name:   pypi
   

3. Create a pypi environment in GitHub: repo → Settings → Environments → New environment → name it pypi
4. That's it — no secrets needed

Troubleshooting

incompatible architecture (have 'arm64', need 'x86_64') on macOS — your terminal is running under Rosetta, so Python picks its x86_64 slice while pip installed arm64 native wheels. Check with arch (should print arm64 on Apple Silicon). Quick fix: prefix the command with arch -arm64. Permanent fix: uncheck "Open using Rosetta" on your terminal app, use an Apple Silicon build of your editor, and restart any long-lived tmux server.

module 'httpx' has no attribute 'AsyncClient' — fixed in 0.3.0-alpha.2; upgrade with pip install --upgrade agentic-ledger.

Port 8000 already in use — another proxy instance (or app) is running; stop it or set AGENTLEDGER_PORT.

401 OAuth access token has expired from Claude Code — the proxy passed Anthropic's answer through unmodified; re-authenticate with claude → /login. Errored calls are still captured, so you'll see the 401 in the dashboard.

/ shows the classic dashboard instead of the web app — you're running from a source checkout without the web-app build. cd dashboard-app && npm ci && npm run build and restart. PyPI and Docker installs always include the app.

License

MIT

mcp-name: io.github.ShekharBhardwaj/agentic-ledger