# Agentlens

> Open-source observability and audit trail platform for AI agents. MCP-native, tamper-evident event logging, real-time dashboard.

- **Type:** MCP server
- **Install:** `agentstack add mcp-agentkitai-agentlens`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [agentkitai](https://agentstack.voostack.com/s/agentkitai)
- **Installs:** 0
- **Category:** [Data & Analytics](https://agentstack.voostack.com/c/data-and-analytics)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [agentkitai](https://github.com/agentkitai)
- **Source:** https://github.com/agentkitai/agentlens
- **Website:** https://agentkitai.github.io/agentlens/

## Install

```sh
agentstack add mcp-agentkitai-agentlens
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

🔍 AgentLens
  
    Open-source observability for AI agents — with a tamper-evident audit trail
    
    Every event SHA-256 hash-chained & cryptographically verifiable — built for EU AI Act Article 12 record-keeping
  
  
    
    
    
    
    
    
  
  
    📖 Documentation · Quick Start · Dashboard · ☁️ Cloud
  

---

## 📑 Table of Contents

- [Tamper-Evident by Design](#-tamper-evident-by-design)
- [Quick Start](#-quick-start)
- [Architecture](#-architecture)
- [Integration Guides](#-integration-guides)
- [Key Features](#-key-features)
- [Dashboard](#-dashboard)
- [AgentLens Cloud](#-agentlens-cloud)
- [Packages](#-packages)
- [API Overview](#-api-overview)
- [CLI](#-cli)
- [Development](#-development)
- [Contributing](#-contributing)
- [AgentKit Ecosystem](#-agentkit-ecosystem)
- [License](#-license)

---

AgentLens is a **flight recorder for AI agents**. It captures every LLM call, tool invocation, approval decision, and error — then presents it through a queryable API and real-time web dashboard.

## 🔒 Tamper-evident by design

What sets AgentLens apart from other observability tools: every event is **SHA-256 hash-chained** to the one before it, the same way git commits and blockchains are linked. The audit log is **append-only and cryptographically verifiable** — alter, delete, or reorder a single record after the fact and verification fails, pointing at the exact event that broke. Purpose-built for the record-keeping obligations of **EU AI Act Article 12** and the emerging **IETF Agent Audit Trail** work.

**See it for yourself in 30 seconds** (needs Docker):

```bash
git clone https://github.com/agentkitai/agentlens && cd agentlens
./demo/aha.sh
```

```text
1/5  Starting AgentLens (SQLite, zero-config)…   ✓ up at http://localhost:3400
2/5  Ingesting a 5-event agent trace…            ✓ 5 events ingested
3/5  Verifying the hash chain…                    ✓ CHAIN VALID — no tampering detected
4/5  Tampering with one event in the database…   ✓ altered llm_call (changed the logged model)
5/5  Re-verifying the hash chain…                 ✗ CHAIN BROKEN — tampering detected ✅
```

The demo ingests a real trace, verifies the chain (passes), edits one record directly in the database behind the audit log's back, then re-verifies (fails). Auditors get a signed, verifiable JSON snapshot from `GET /api/audit/verify/export`.

**Five ways to integrate — pick what fits your stack:**

| Integration | Language | Effort | Capture |
|---|---|---|---|
| 🔭 **[OpenTelemetry](#-opentelemetry-any-genai-agent--no-sdk)** | Any | **Point your OTLP exporter** | Any `gen_ai.*`-instrumented agent — **no AgentLens SDK** |
| 🤖 **[OpenClaw Plugin](#-openclaw-plugin)** | [OpenClaw](https://github.com/openclaw/openclaw) | **Copy & enable** | Every Anthropic call — prompts, tokens, cost, tools — zero code |
| 🐍 **[Python Auto-Instrumentation](#-python-auto-instrumentation)** | Python | **1 line** | Every OpenAI / Anthropic / LangChain call — deterministic |
| 🔌 **[MCP Server](#-mcp-integration)** | Any (MCP) | Config block | Tool calls, sessions, events from Claude Desktop / Cursor |
| 📦 **[SDK](#-programmatic-sdk)** | Python, TypeScript | Code | Full control — log events, query analytics, build integrations |

## 🚀 Quick Start

**One command** — server + dashboard on SQLite, zero config:

```bash
docker run -p 3400:3400 -e AUTH_DISABLED=true -e JWT_SECRET=dev-secret ghcr.io/agentkitai/agentlens
# Open http://localhost:3400
```

Or without Docker:

```bash
npx @agentkitai/agentlens-server
# http://localhost:3400 with SQLite — zero config
```

> `AUTH_DISABLED=true` is for a quick local trial (`JWT_SECRET` is still required by the hardened image). For anything shared, drop `AUTH_DISABLED`, set a real `JWT_SECRET`, and create an API key (below).

**Full stack** (Postgres + Redis, auth, TLS) — runs from source:

```bash
git clone https://github.com/agentkitai/agentlens && cd agentlens
cp .env.example .env
docker compose up
# production overlay (auth, restart policies):
docker compose -f docker-compose.yml -f docker-compose.prod.yml up
```

### Create an API Key

```bash
curl -X POST http://localhost:3400/api/keys \
  -H "Content-Type: application/json" \
  -d '{"name": "my-agent"}'
```

Save the `als_...` key from the response — it's shown only once. Then head to the [Integration Guides](#-integration-guides) to instrument your agent.

📖 [Full setup guide →](./docs/guide/)

## 🏗️ Architecture

```mermaid
graph TB
    subgraph Agents["Your AI Agents"]
        PY["Python App(OpenAI, Anthropic, LangChain)"]
        MCP_C["MCP Client(Claude Desktop, Cursor)"]
        TS["TypeScript App"]
        OC["OpenClaw Plugin"]
    end

    PY -->|"agentlensai.init()auto-instrumentation"| SERVER
    MCP_C -->|MCP Protocol| MCP_S["@agentkitai/agentlens-mcp"]
    MCP_S -->|HTTP| SERVER
    TS -->|"@agentkitai/agentlens-sdk"| SERVER
    OC -->|HTTP| SERVER

    subgraph Server["@agentkitai/agentlens-server"]
        direction TB
        INGEST[Ingest Engine]
        QUERY[Query Engine]
        ALERT[Alert Engine]
        LLM_A[LLM Analytics]
        HEALTH[Health Scoring]
        COST[Cost Optimizer]
        REPLAY[Session Replay]
        BENCH[Benchmark Engine]
        GUARD[Guardrails]
    end

    SERVER --> DB[(SQLite / Postgres)]
    SERVER --> DASH["Dashboard(React SPA)"]

    EXT["AgentGate / FormBridge"] -->|Webhook| SERVER
```

## 🔧 Integration Guides

### 🔭 OpenTelemetry (any GenAI agent — no SDK)

If your agent is already instrumented with the **[OpenTelemetry GenAI semantic conventions](https://opentelemetry.io/docs/specs/semconv/gen-ai/)** — via OpenLLMetry, OpenInference, or the official OTel instrumentations — just point its OTLP exporter at AgentLens. **No AgentLens SDK required.**

```bash
# Send standard OTLP/HTTP to AgentLens (JSON or protobuf, /v1/traces)
export OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:3400
export OTEL_EXPORTER_OTLP_TRACES_ENDPOINT=http://localhost:3400/v1/traces
```

AgentLens maps `gen_ai.*` spans into its model and into the tamper-evident audit log:

| OTel GenAI span (`gen_ai.operation.name`) | Becomes |
|---|---|
| `chat` / `text_completion` / `generate_content` | a paired `llm_call` + `llm_response` (model, provider, messages, `usage.input_tokens`/`output_tokens`, finish reason, latency, **cost**) |
| `execute_tool` | `tool_call` (`gen_ai.tool.name`, `gen_ai.tool.call.id`, arguments) |
| `embeddings` | embedding event with token usage |
| `invoke_agent` / `create_agent` | agent-invocation event |

Each OTel **trace** maps to a session (or `gen_ai.conversation.id` if present), and every event is hash-chained like any other — so traces from any GenAI framework get the same verifiable audit trail. Set `OTLP_AUTH_TOKEN` to require a bearer token on the OTLP endpoints in production.

> **Cost with no SDK:** OTel GenAI instrumentation reports tokens but rarely cost. AgentLens reconstructs `costUsd` from the model's per-1M-token pricing (fuzzy-matched on the model id), so OTel-only agents get the same cost analytics as SDK-instrumented ones — no per-call cost attribute required.

### 🤖 OpenClaw Plugin

If you're running [OpenClaw](https://github.com/openclaw/openclaw), the AgentLens plugin captures every Anthropic API call automatically — prompts, completions, token usage, costs, latency, and tool calls.

```bash
cp -r packages/relay-plugin /usr/lib/node_modules/openclaw/extensions/agentlens-relay
openclaw config patch '{"plugins":{"entries":{"agentlens-relay":{"enabled":true}}}}'
openclaw gateway restart
```

Set `AGENTLENS_URL` if your AgentLens instance isn't on `localhost:3400`. See the [plugin README](./packages/relay-plugin/README.md) for details.

### 🐍 Python Auto-Instrumentation

One line — every LLM call captured automatically across **9 providers** (OpenAI, Anthropic, LiteLLM, AWS Bedrock, Google Vertex AI, Google Gemini, Mistral AI, Cohere, Ollama):

```bash
pip install agentlensai[all-providers]
```

```python
import agentlensai

agentlensai.init(
    url="http://localhost:3400",
    api_key="als_your_key",
    agent_id="my-agent",
)
# Every LLM call is now captured automatically
```

**Key guarantees:** ✅ Deterministic · ✅ Fail-safe · ✅ Non-blocking · ✅ Privacy (`init(redact=True)`)

📖 [Python SDK full docs →](./docs/guide/)

### 🔌 MCP Integration

For Claude Desktop, Cursor, or any MCP client — add to your config:

```json
{
  "mcpServers": {
    "agentlens": {
      "command": "npx",
      "args": ["@agentkitai/agentlens-mcp"],
      "env": {
        "AGENTLENS_API_URL": "http://localhost:3400",
        "AGENTLENS_API_KEY": "als_your_key_here"
      }
    }
  }
}
```

AgentLens ships **22 MCP tools** — covering core observability, intelligence & analytics, and operations. [Full MCP tool reference →](./docs/reference/api.md)

📖 [MCP setup guide →](./docs/guide/)

### 📦 Programmatic SDK

**Python:**
```bash
pip install agentlensai
```
```python
from agentlensai import AgentLensClient
client = AgentLensClient("http://localhost:3400", api_key="als_your_key")
sessions = client.get_sessions()
analytics = client.get_llm_analytics()
```

**TypeScript:**
```bash
npm install @agentkitai/agentlens-sdk
```
```typescript
import { AgentLensClient } from '@agentkitai/agentlens-sdk';
const client = new AgentLensClient({ baseUrl: 'http://localhost:3400', apiKey: 'als_your_key' });
const sessions = await client.getSessions();
```

📖 [SDK reference →](./docs/reference/api.md)

## ✨ Key Features

- **🐍 Python Auto-Instrumentation** — `agentlensai.init()` captures every LLM call across 9 providers automatically. Deterministic — no reliance on LLM behavior.
- **🔌 MCP-Native** — Ships as an MCP server. Works with Claude Desktop, Cursor, and any MCP client.
- **🔭 OpenTelemetry GenAI** — Ingests `gen_ai.*` OTLP traces from any OTel-instrumented agent (OpenLLMetry, OpenInference, official OTel) — no AgentLens SDK required.
- **🧠 LLM Call Tracking** — Full prompt/completion visibility, token usage, cost aggregation, latency measurement, and privacy redaction.
- **📊 Real-Time Dashboard** — Session timelines, event explorer, LLM analytics, cost tracking, and alerting.
- **🔒 Tamper-Evident Audit Trail** — Append-only event storage with SHA-256 hash chains per session.
- **💰 Cost Tracking** — Track token usage and estimated costs per session, per agent, per model. Alert on cost spikes.
- **🚨 Alerting** — Configurable rules for error rate, cost threshold, latency anomalies, and inactivity.
- **❤️‍🩹 Health Scores** — 5-dimension health scoring with trend tracking.
- **💡 Cost Optimization** — Complexity-aware model recommendation engine with projected savings.
- **📼 Session Replay** — Step-through any past session with full context reconstruction.
- **⚖️ A/B Benchmarking** — Statistical comparison of agent variants using Welch's t-test and chi-squared analysis.
- **🛡️ Guardrails** — Automated safety rules with dry-run mode for safe testing.
- **🔌 Framework Plugins** — LangChain, CrewAI, AutoGen, Semantic Kernel — auto-detection, fail-safe, non-blocking.
- **🔗 AgentKit Ecosystem** — Integrations with [AgentGate](https://github.com/agentkitai/agentgate), [FormBridge](https://github.com/agentkitai/formbridge), [Lore](https://github.com/agentkitai/lore), and [AgentEval](https://github.com/agentkitai/agenteval).
- **🔒 Tenant Isolation** — Multi-tenant support with per-tenant data scoping and API key binding.
- **🏠 Self-Hosted** — SQLite by default, no external dependencies. MIT licensed.

## 📸 Dashboard

AgentLens ships with a real-time web dashboard for monitoring your agents.

📸 Dashboard Screenshots (click to expand)

### Overview — At-a-Glance Metrics

The overview page shows **live metrics** — sessions, events, errors, and active agents — with a 24-hour event timeline chart, recent sessions with status badges, and a recent errors feed.

### Sessions — Track Every Agent Run

Every agent session with sortable columns: agent name, status, start time, duration, event count, error count, and total cost.

### Session Detail — Timeline & Hash Chain

Full event timeline with tamper-evident hash chain verification. Filter by event type, view cost breakdown.

### Events Explorer — Search & Filter Everything

Searchable, filterable view of every event across all sessions.

### 🧠 LLM Analytics — Prompt & Cost Tracking

Total LLM calls, cost, latency, and token usage across all agents with model comparison.

### 🧠 Session Timeline — LLM Call Pairing

LLM calls in session timeline with model, tokens, cost, and latency.

### 💬 Prompt Detail — Chat Bubble Viewer

Full prompt and completion in a chat-bubble style viewer with metadata panel.

### ❤️‍🩹 Health Overview — Agent Reliability

5-dimension health score for every agent with trend tracking.

### 💡 Cost Optimization — Model Recommendations

Analyzes LLM call patterns and recommends cheaper model alternatives with confidence levels.

### 📼 Session Replay — Step-Through Debugger

Step through any past session event by event with full context reconstruction.

### ⚖️ Benchmarks — A/B Testing for Agents

Create and manage A/B experiments with statistical significance testing.

### 🛡️ Guardrails — Automated Safety Rules

Create and manage automated safety rules with trigger history and activity feed.

## ☁️ AgentLens Cloud

Don't want to self-host? **AgentLens Cloud** is a fully managed SaaS — same SDK, zero infrastructure:

```python
import agentlensai
agentlensai.init(cloud=True, api_key="als_cloud_your_key_here", agent_id="my-agent")
```

- **Same SDK, one parameter change** — switch `url=` to `cloud=True`
- **Managed Postgres** — multi-tenant with row-level security
- **Team features** — organizations, RBAC, audit logs
- **No server to run** — dashboard at [app.agentlens.ai](https://app.agentlens.ai)

📖 [Cloud Setup Guide](./docs/guide/cloud-setup.md) · [Migration Guide](./docs/guide/cloud-migration.md) · [Troubleshooting](./docs/guide/troubleshooting.md)

## 📦 Packages

### Python (PyPI)

| Package | Description | PyPI |
|---|---|---|
| [`agentlensai`](./packages/python-sdk) | Python SDK + auto-instrumentation for 9 LLM providers | [](https://pypi.org/project/agentlensai/) |

### TypeScript / Node.js (npm)

| Package | Description | npm |
|---|---|---|
| [`@agentkitai/agentlens-server`](./packages/server) | Hono API server + dashboard serving | [](https://npmjs.com/package/@agentkitai/agentlens-server) |
| [`@agentkitai/agentlens-mcp`](./packages/mcp) | MCP server for agent instrumentation | [](https://npmjs.com/package/@agentkitai/agentlens-mcp) |
| [`@agentkitai/agentlens-sdk`](./packages/sdk) | Programmatic TypeScript client | [](https://npmjs.com/package/@agentkitai/agentlens-sdk) |
| [`@agentkitai/agentlens-core`](./packages/core) | Shared types, schemas, hash chain utilities | [](https://npmjs.com/package/@agentkitai/agentlens-core) |
| [`@agentkitai/agentlens-cli`](./packages/cli) | Command-line interface | [](https://npmjs.com/package/@agentkitai/agentlens-cli) |
| [`@agentkitai/agentlens-dashboard`](./packages/dashboard) | React web dashboard (bundled with server) | private |

## 🔌 API Overview

| Endpoint | Description |
|---|---|
| `POST /api/events` | Ingest events (batch) |
| `GET /api/events` | Query events with filters |
| `GET /api/sessions` | List sessions |
| `GET /api/sessions/:id/timeline` | Session timeline with hash chain verification |
| `GET /api/analytics` | Bucketed metrics over time |

[Full API Reference →](./docs/reference/api.md)

## ⌨️ CLI

```bash
npx @agentkitai/agentlens-cli health                          # Overview of all agents
npx @agentkitai/agentlens-cli health --agent my-agent          # Detailed health with dimensions
npx @agentkitai/agentlens-cli optimize                          # Cost optimization recommendations
```

Both commands support `--format json` for machine-readable output. See `agentlens health --help` for all options.

## 🛠️ Development

```bash
git clone https://githu

…

## Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [agentkitai](https://github.com/agentkitai)
- **Source:** [agentkitai/agentlens](https://github.com/agentkitai/agentlens)
- **License:** MIT
- **Homepage:** https://agentkitai.github.io/agentlens/

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** yes
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** yes
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/mcp-agentkitai-agentlens
- Seller: https://agentstack.voostack.com/s/agentkitai
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.