StartupSeed
Entire
A Git forge for agent-human collaboration that versions the reasoning behind code.
Entire, led by former GitHub CEO Thomas Dohmke, is a Git-compatible forge that stores the reasoning behind changes alongside code. Its open-source CLI (first released as Checkpoints) captures agent sessions such as prompts, tools used and token use, initially from Claude Code and Gemini CLI. The forge adds 'Trails' as a pull-request replacement with agent reviews and evals, code-graph plus session memory for agent context, agentic search across code, commits and sessions, and secret redaction. It raised a $60M seed led by Felicis in February 2026.
Pros & cons
Each point cites its sources and says what kind of evidence backs it. A second reviewer tried to refute every claim before it was kept.
Pros
- MetadataIts Checkpoints CLI is MIT-licensed and actively developed (about 5K stars), capturing agent prompts, transcripts and tool calls next to each commit.[1][2]
- DocsStores session metadata on a separate entire/checkpoints/v1 branch, so your working history stays clean while you keep an append-only audit log.[1][2]
- DocsSupports several agents (Claude Code, Gemini CLI, Cursor, Copilot CLI), with rewind and resume of earlier sessions.[1]
Cons
- User reportsHN users point out that for Claude Code the captured data is just the local JSONL transcript, which a simple commit hook could push.[1]
- User reportsSome find storing metadata on a side branch clunky for enforcing that every push carries its reasoning.[1]
- Independent testStill early: reviewers note limited dashboard visualisation and edge cases with large repos and high-frequency sessions, and the full platform is not out yet.[1][2]
- Best for
- Teams that want an auditable record of why agent-written code changed, kept inside git.
- Watch out for
- Pushing prompts and transcripts into the repo can expose sensitive context, and the hosted platform is still forming.
Assessed Oct 29, 2026 · adversarially reviewedSuggest a correction
People
Founder & CEO
Harness engineering
In research (1)
Oct 26, 2026 · Entire's session checkpoints (prompts and tool calls stored alongside commits) are a key mechanism reviewed.
Neighbours in the directory
San Francisco, CA · Est. 2023
Devin, the AI software engineer, and the Windsurf IDE.
Cognition builds Devin, an autonomous AI software engineer that plans and executes engineering tasks end-to-end, and acquired the Windsurf agentic IDE in 2025. One of the defining startups of the coding-agent wave.
~$10.2B valuation (Sep 2025)
Berkeley, CA · Est. 2024
Stateful agents with memory, from the team behind MemGPT.
Letta (formerly MemGPT, out of UC Berkeley) builds an agent server with built-in memory, context management and state — letting agents persist, learn and be edited like files rather than living in a chat window.
$10M seed led by Felicis (2024)
San Francisco, CA · Est. 2023
The integration layer: hundreds of managed tools your agents can call.
Composio handles auth, schemas, observability and reliability for the external SaaS tools an agent uses — 'plumbing for agentic actions' across Slack, GitHub, Salesforce and 250+ other surfaces.
Connections
Relations from the Harness Hub knowledge graph, as charted in the State of Harness reports.
Built on · 2
- Claude CodeProject
- Gemini CLIProject
Sources
Verified Oct 29, 2026