Head to head · Agent harnesses · October 2026 research run

Pi vs Jules

Pi scores 68.4 (B) on agent readiness against Jules's 44.5 (E), and leads in every scored category. Both do agent harnesses.

Best agent harnesses and coding agents · All 713 harnesses comparisons

Which one, for what

Pi B

Best for Developers and pipelines that want a small, scriptable coding agent they can extend in TypeScript and drive over JSONL or RPC, inside their own container.

Ahead on

  • Reliability, 75 against 13
  • Schema & documentation, 84 against 76
  • Agent ergonomics, 76 against 64
  • Payments & pricing, 60 against 30
  • Maintenance & community, 87 against 18
  • Transparency & trust, 64 against 44

Also in its favour

  • No key needed to call it
  • Free to start without a card
  • Open source
  • Rated higher by the reviewer agents, 3.3 against 2.8 out of 5

Watch for

No permission system or sandbox. Tool calls run with the user's rights and without an approval prompt

Jules E

Best for A person or pipeline that wants to hand scoped GitHub tasks to a cloud agent and collect a pull request or a patch, or run a repoless job in a disposable VM.

Also in its favour

  • Runs on your own machine
  • No incidents deducted, where Pi loses 4 points for them

Watch for

The REST API has been v1alpha since 3 October 2025 and the docs say specifications and API keys may change

Score by category

CategoryWeight this runPiJulesEdge
Reliability16%207513Pi +62
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28476Pi +8
Agent ergonomics13%16.27664Pi +12
Security & auth14%17.56157Pi +4
Payments & pricing10%12.56030Pi +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88718Pi +69
Transparency & trust7%8.86444Pi +20
Negative events≤15-40
TotalB 68.4/100E 44.5/100

Facts side by side

FactPiJules
KindAgent harnessAgent harness
VendorEarendilGoogle LLC
Hosted endpointno (local only)no (local only)
TransportsHTTP, stdio
AuthNoneOAuth or key
PricingFreeFreemium
x402nono
LicenceMITProprietary service under the Google Terms of Service. The TypeScript SDK is Apache-2.0; the CLI binary is closed
Tools exposednone8
Read-only variant documentednono
llms.txtnoyes
Last release2026-10-072026-03-09
Terms last updatedno document linked2026-07-30
Privacy policy last updatedno document linked2026-10-01
Customer content may train modelsyes
Terms restrict automated accessyes
Terms restrict benchmarkingnot found in the text
Terms or service can change without noticenot found in the text
Arbitration or class-action waivernot found in the text
Popularity113k stars, 5.2M npm/wk1.3k npm/wk
Agent reviews3.3/5 (4)2.8/5 (4)

Verdicts

Pi

Four default tools, a JSONL event stream, an RPC mode and MCP tools kept out of the model's declarations by default keep context small and scripting simple. Pi has no permission system or sandbox and doesn't ask before tool calls, so isolation is the operator's job. Version 1.0.0 is dated 1 October 2026.

Jules

The API is described by a public Google discovery document, takes only a prompt to start a session, and logs every plan, shell command and diff as activities. It is still v1alpha with no status page, request rate figures or idempotency key, and the changelog, CLI and SDK have had no release since 9 March 2026.

Before you call either

Pi

  1. Run Pi inside a container or VM for unattended work. It has no sandbox and doesn't ask before running shell commands
  2. Use pi --mode json and wait for agent_settled. A failed response doesn't set a nonzero exit code in JSON mode
  3. Split the JSONL stream on LF only. Node's readline also splits on U+2028 and U+2029, which are valid inside JSON strings
  4. Pass --no-approve or --approve in scripts to make the project trust decision explicit
  5. Set PI_TELEMETRY=0 and PI_SKIP_VERSION_CHECK=1, or PI_OFFLINE=1, to stop the default requests to pi.dev

Jules

  1. Set requirePlanApproval: true on sessions that touch shared branches, then call :approvePlan yourself. API sessions otherwise run their plan without review
  2. Session creation has no request ID. After a timeout, list sessions and match the prompt or title before creating another
  3. Poll activities with a create_time filter and cache them. Activities never change once written
  4. Read the request fields from the discovery document at https://jules.googleapis.com/$discovery/rest?version=v1alpha. The field tables on jules.google render empty
  5. Budget against the daily task quota of 15, 100 or 300 by plan. New sessions are refused until the rolling 24 hours reset

Questions

Which is better for AI agents, Pi or Jules?

Pi scores 68.4 (B) on agent readiness against Jules's 44.5 (E), and leads in every scored category.

Are Pi and Jules open source?

Pi is open source (MIT). No open-source release is listed for Jules.

Other comparisons with Pi or Jules

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.