Harness Hub
All startups

Unblocked

The context layer for agentic software development.

Unblocked merges code, conversations, issues, docs, product data and production systems into one knowledge graph and resolves conflicts between sources using recency, authority and proximity, so agents know what to trust. Its Organizational Memory mines team conventions from PR review feedback and history, results are permission-scoped with source links, and it is accessed via MCP (Cursor, Claude Code, Copilot), CLI, Slack, web and API. The Vancouver company, led by founder and CEO Dennis Pilarinos, raised a $20M USD Series A led by B Capital in May 2025.

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

  • DocsBuilds one context model from code, PRs, Slack, Jira, Notion and Confluence, and reviews each change against it.[1]
  • DocsThe Code Review tier (about $19/user/month annually) includes unlimited reviews, PR summaries and a CI-failure agent.[1][2]
  • DocsA higher tier exposes the context through MCP and chat, so coding agents can query team knowledge.[1]

Cons

  • DocsNo permanent free tier, only a 21-day trial.[1]
  • DocsCode review is limited to supported GitHub and GitLab repositories.[1]
  • DocsPer-seat pricing ($29-$35/user/month for the platform tier) adds up across large teams.[1]
  • MetadataMost comparative claims come from Unblocked's own blog, and independent user discussion is sparse.[1]
Best for
Teams whose tribal knowledge lives in Slack, Jira and Confluence and want that context in reviews and agents.
Watch out for
Granting broad read access to internal tools, and per-seat costs.

Assessed Oct 29, 2026 · adversarially reviewedSuggest a correction

People

Featured

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)

3 pros · 4 cons

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)

4 pros · 3 cons

The AI-native code editor where agent mode lives.

Cursor rebuilt the IDE around models: tab completion, in-editor chat and agent mode that plans multi-file edits and runs commands. Its rise set the pace for the entire coding-agent market.

~$29B valuation (late 2025)

3 pros · 4 cons

Connections

Relations from the Harness Hub knowledge graph, as charted in the State of Harness reports.

Built on · 2

Sources

  1. Unblocked homepage
  2. BetaKit: Unblocked raises $27.5M CAD Series A