Vol. 01 — Local-first
Your logs never leave your machine

Cut your coding agent's token costs by up to 90%.

AgentLogs analyzes your agent session logs and turns them into artifacts and context that make your coding agents run leaner — fewer loops, faster error fixes, and far lower token bills.

$curl -fsSL https://agentlogs.promptingco.com/install.sh | sh
agentlogs analyze codex
$ agentlogs analyze codex --since 7d
scanning ~/.codex/sessions … 14 sessions
signal verification-status
verified_after_final_edit · 8 sessions
verification_skipped · 4 sessions
blocked_env_missing · 2 sessions
evidence: session_abc · event 72 · bun test exited 0
37% of sessions missing verification
The pipeline

Every signal stays grounded in evidence

AgentLogs runs a small, auditable kernel. Raw events flow into scoped views, get reduced into typed signals, and surface as findings — and every step points back to the events that produced it.

  1. 01Source~/.codex/sessions
  2. 02Artifactone session
  3. 03Eventmessages, commands, edits
  4. 04Segmentscoped windows
  5. 05ProjectioncompactTimeline, failedCommands
  6. 06Extractorlocal rules or LLM
  7. 07Signaltyped + evidence
  8. 08Findinghuman insight
  9. 09Reporttext, JSON, Markdown
Extractor

what signal logic runs

Backend

where extraction executes

Adapter

how it talks to a model

Extractor identity is separate from backend identity. The same verification-status signal runs through local rules, a local Ollama model, or a remote backend — without changing the raw evidence model.

Why AgentLogs

Audit agent runs, don't re-read them

Built around a signal-analysis kernel that keeps structured observations grounded in raw, auditable evidence.

Local-first by default

01

Discovers and analyzes sessions on your machine. There's no hosted service to sign up for and no requirement to send raw logs anywhere.

Evidence on every signal

02

Each signal carries pointers back to the exact events — session id, event index, command output — that justify it. No claim without proof.

Map / reduce on long sessions

03

Long transcripts are split into deterministic windows, projected into focused views, then folded into session-level signals — not stuffed into one prompt.

Backend-neutral extraction

04

Run the same signal definition through local rules, a local model, or a remote backend. Extractor identity is decoupled from where it executes.

Reproducible reports

05

Provenance records the extractor version, prompt version, model, and config hash, so a report can be regenerated from a frozen analysis run.

Codex today, more to come

06

The first source adapter reads Codex session history. The shared kernel is domain-neutral, ready for other coding agents without reinventing the vocabulary.

The contract

Evidence answers “what supports this?” — provenance answers “how was it produced?”

Every signal is structured data with both — so results are auditable and reproducible, never a black box.

commands
$ agentlogs analyze codex --since 7d
$ agentlogs analyze codex --session latest --backend local-rules
$ agentlogs analyze codex --since 24h --limit 3 --format json
$ agentlogs version --format json
Flags
--since
7d, 24h — time window to scan
--session
latest or a session id
--limit
cap the number of sessions
--format
text or json output
--backend
where extraction runs
signal.json
{
  "signalId": "verification-status",
  "scope": "artifact",
  "value": "verified_after_final_edit",
  "confidence": 0.91,
  "evidence": [
    { "eventIndex": 55, "snippet": "apply_patch bar.ts" },
    { "eventIndex": 72, "snippet": "bun test exited 0" }
  ],
  "provenance": {
    "extractor": "verification-status",
    "extractorVersion": 1,
    "model": "qwen2.5-coder:14b",
    "configHash": "sha256:…"
  }
}
Get started

Install AgentLogs

Free and local. Point it at your Codex sessions and read your first report in seconds.

macOS / Linux
$ curl -fsSL https://agentlogs.promptingco.com/install.sh | sh
Windows (PowerShell)
$ irm https://agentlogs.promptingco.com/install.ps1 | iex
From source
$ go install github.com/promptingcompany/agentlogs@latest