Codag
Sign in Book a demo

Log compression for AI agents

Pay 95% less in tokens to read your logs
at no accuracy loss.

Codag is a drop-in compression and incident-memory layer for AI agents. We can collapse a million log lines into one schema-valid capsule before your LLM sees them, and cluster recurring incidents over time so the next outage triages by recalling the last one.

Wrap any log call your agent already makes, no hassle.

Book a demo Sign in

PRIVATE BETA · API KEYS BY APPROVAL

24.6M tokens
1,247,392 lines · 198 MB
Raw logs
1 hour window
847 tokens
1 capsule · 18 evidence lines
IncidentCapsule
schema-valid JSON
2026-05-04T14:22:11Z INFO pod/api-7f9 starting...
2026-05-04T14:22:11Z INFO loaded config /etc/api
2026-05-04T14:22:12Z INFO postgres pool size=20
2026-05-04T14:22:12Z INFO redis ping ok 0.6ms
2026-05-04T14:22:13Z INFO health probe ok 200
2026-05-04T14:22:14Z INFO request id=abc123 path=/v1/users
2026-05-04T14:22:14Z INFO cache hit user:42
2026-05-04T14:22:15Z WARN pool acquire 240ms
2026-05-04T14:22:16Z WARN pool acquire 480ms
2026-05-04T14:22:16Z ERROR psycopg2.OperationalError: connection
2026-05-04T14:22:17Z ERROR retry 1/3 db_users
2026-05-04T14:22:17Z INFO request id=abc124 path=/v1/orders
2026-05-04T14:22:18Z ERROR retry 2/3 db_users
2026-05-04T14:22:18Z ERROR upstream timeout id=abc124
2026-05-04T14:22:19Z INFO cache miss user:99
2026-05-04T14:22:19Z WARN circuit breaker open svc=db
2026-05-04T14:22:20Z INFO request id=abc125 path=/v1/users
2026-05-04T14:22:20Z ERROR pool exhausted, queue=18
2026-05-04T14:22:21Z INFO retry succeeded id=abc126
2026-05-04T14:22:21Z WARN p99 latency 2840ms
2026-05-04T14:22:22Z INFO cache miss user:51
+ 1,247,371 more lines …
{
  "service": "api",
  "window": "14:22:11–15:22:11",
  "compression": 29063,
  "evidence": [
    {
      "role": "root_cause",
      "line": 412847,
      "text": "psycopg2.OperationalError"
    },
    {
      "role": "trigger",
      "line": 412831,
      "text": "pool acquire 480ms"
    },
    {
      "role": "consequence",
      "line": 412854,
      "text": "pool exhausted, queue=18"
    }
    // + 15 more, all cited
  ]
}

Pairs with any agent

Anthropic OpenAI Gemini Groq Ollama Cohere Mistral AWS OpenRouter

For Claude Code users

You debug logs in Claude Code.
Pay less. See more.

Wrap any log fetch your agent already makes. Same Claude. Same answers. A fraction of the token bill, and bigger context windows for the lines that actually matter.

Token cost · per incident

Raw logs $369
Wrapped with codag $0.013
29,000×

cheaper per incident

@ Opus 4.7 rates · 1.2M lines · 24.6M → 847 tokens

Setup · 2 commands

terminal 
  # 1. Install
  $ curl -fsSL https://codag.ai/install.sh | bash

  # 2. Auth + write .mcp.json
  $ codag init
  ✓ Created .mcp.json (Claude Code)
    Your agent now reads logs through Codag.

→ MCP server wired automatically. No config files to edit.