StartupPalo Alto, CA · Est. 2022 · Series B
Augment Code
Always-on software delivery agents built on shared codebase context.
Augment Code (Augment Computing Inc.) builds AI coding agents for professional engineering teams. Its Cosmos platform is pitched as an always-on software delivery system from spec to verification, with pre-built agent loops for code review, ticket-to-PR, vulnerability remediation and incident response. Work is triggered from GitHub, GitLab, Slack, Linear, Jira, schedules or webhooks, runs in managed cloud sandboxes or customer-managed machines, and carries permissions, audit trails, observability and human review points, with per-task model choice. Founded in 2022 by Igor Ostrovsky and Guy Gur-Ari.
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
- User reportsIts Context Engine is repeatedly praised for finding the right places to change in large codebases without manual planning.[1][2]
- User reportsThe Context Engine is also offered over MCP, so other agents can query the pre-indexed codebase in natural language.[1][2]
- User reportsWorks as a plugin for both JetBrains IDEs and VS Code rather than requiring a forked editor.[1]
Cons
- DocsThe October 2025 move from messages to credits raised costs for heavy users, as Augment itself acknowledged.[1][2]
- Independent testMonthly credits do not roll over, and users must pick a plan before they know their usage.[1]
- User reportsUsers report surprise consumption, such as 51K credits gone in one day, and call the change bait-and-switch.[1][2]
- MetadataPlans have changed several times in under a year, including dropping the free tier, which makes budgeting hard.[1][2]
- Best for
- Developers on large, unfamiliar codebases who want strong codebase retrieval inside their existing IDE.
- Watch out for
- Credit burn and frequent pricing changes.
Assessed Oct 29, 2026 · adversarially reviewedSuggest a correction
People
17.6K subscribers
Official YouTube channel
Context engineering & memory · Multi-agent orchestration
Co-founder & Chief Scientist
Harness engineering
Co-founder
Harness engineering
Executive
CEO
Harness engineering
Neighbours in the directory
San Francisco, CA · Est. 2022
The de-facto standard toolkit for building LLM applications and agents.
LangChain makes the LangChain framework and LangGraph, the low-level orchestration standard for stateful, controllable agents, plus the LangSmith platform for tracing, evaluating and monitoring them in production.
~$75M raised
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)
San Francisco, CA · Est. 2023
Conversational AI agents for customer experience.
Sierra, co-founded by Bret Taylor and Clay Bavor, builds production conversational agents that resolve real customer issues with guardrails, evaluation and human escalation — a template for deploying vertical agents at the enterprise edge.
~$10B valuation (Oct 2025)
Sources
Verified Oct 29, 2026