Codag is a developer tool that compresses infrastructure log data into structured incident summaries for AI agents. It converts large volumes of system logs into compact, schema-valid JSON capsules optimized for LLM context windows. Codag is part of Y Combinator's Summer 2026 batch and is based in San Francisco.
Codag
ActiveSystems log compression for agents
Total raised
$500K
1 round
Stage
Seed
Jan 2026
Team
1-10
since 2026
Pricing
—
Founded
2026
San Francisco, United States
Agent-ready
—
Compresses high-volume infrastructure and system logs into compact incident summaries
Outputs schema-valid JSON capsules designed for LLM ingestion
Optimizes payloads to fit within LLM context windows
Structures unstructured log streams into consistent, machine-readable formats
Targets observability and incident-response workflows for AI agents
Reduces token consumption when feeding logs to language models
Developer-oriented tooling for integration into agent pipelines
Built to summarize logs across distributed systems and infrastructure sources
12/100
Early
MCP server
Public API
Webhooks
OAuth 2.0
SDKs
No public agent surfaces detected yet.
Jan 2026 Seed $500K ● Y Combinator
Capital network
$500K raised ·1 backer·10 network links
- Backers1
- Shared portfoliocompanies these backers also fund
- Extended networkfunds that co-invest alongside them
Databricks
The data + AI company
AI AgentsAI Infrastructure
Figure AI
General-purpose humanoid robots
AI InfrastructureAI Robotics
Upscale AI
Pure-play AI networking infrastructure
AI Developer ToolsAI Infrastructure
Dash0
AI-native observability platform built on OpenTelemetry
AI InfrastructureAI Data Engineering
Noma Security
End-to-end security for agentic AI
AI InfrastructureAI for Cyber Defense
Ineffable Intelligence
An AI research company building a superlearner to achieve superintelligence through reinforcement learning
Foundation ModelsAI Infrastructure
- What problem does Codag solve?
- Raw infrastructure logs are too large and noisy to fit efficiently into LLM context windows. Codag compresses them into compact, structured incident summaries so AI agents can reason over them without exceeding token limits.
- What format does Codag output?
- It produces schema-valid JSON capsules, which are structured and predictable so downstream agents and tools can parse them reliably.
- Who is Codag built for?
- It is a developer tool aimed at teams building AI agents for observability, incident response, and infrastructure log analysis.
- Is Codag an established product?
- Codag is an early-stage startup based in San Francisco and part of Y Combinator's Summer 2026 batch.
Discussion
Sign in to join the discussion.
Sign inExplore more around Codag
Contextual paths to related AI startups, deals and rankings.