Harrison Chase started LangChain in late 2022 as a side project: a single Python package pushed from a personal GitHub account. In early 2023 Chase and co-founder Ankush Gola started LangChain, the company, which has since released LangGraph for building agent systems, the LangSmith platform for agent observability and evaluation, and the Deep Agents harness. The open-source LangChain framework is published under the MIT license, and Chase writes the "Harrison's In the Loop" series on the LangChain blog.1234
At a glance
- Current role
- Co-founder
- Company
- LangChain
- Sector
- Company
- Fields
- Agents, Developer tools, Language models
- Work listed
- 2
- Sources cited
- 7
- Profile reviewed
Open-source work
Chase made the initial commit to the LangChain repository on October 24, 2022, when the project was a single Python package. The repository, now hosted by the langchain-ai organization and released under the MIT license, describes LangChain as an agent engineering platform.5231
In July 2025 Chase made the initial commits to Deep Agents, which the repository describes as a batteries-included agent harness and which the company presents as its harness for autonomous, long-horizon tasks. Like LangChain and LangGraph, a low-level orchestration framework for stateful agents, it is released under the MIT license.617
Products and projects
Chase and Ankush Gola founded LangChain as a company in early 2023. Following the framework, the company launched LangGraph to give developers control over complex agent systems, and LangSmith, a commercial platform for agent observability that later added evaluation, deployment and a no-code agent builder.1
Writing
Chase writes "Harrison's In the Loop", a series of essays on the LangChain blog about building and running AI agents in companies, such as a July 2026 piece on what it means for a business to own the models, context and memory behind its AI systems.4
Work and contributions
LangChain (framework) Open-source code
LangChain's company page says the project started as Chase's side project in late 2022, as a single Python package pushed from a personal GitHub account. The framework repository is published under the MIT license.123
Deep Agents Open-source code
Made the initial commits in July 2025 to the MIT-licensed agent harness, which LangChain describes as built for autonomous, long-horizon tasks.61
Timeline
- Made the initial commit to the LangChain repository.5
- Co-founded LangChain, the company, with Ankush Gola.1
- LangChain created the LangGraph repository for building stateful agents.7
- Made the initial commit to Deep Agents, LangChain's open-source agent harness.6
- Published the In the Loop essay on owning the intelligence behind company AI systems.4
Where they work
- LangChain 1 person in the wiki
Related people
- Graham NeubigAgents · Language models
- Binyuan HuiAgents · Language models
- Michele CatastaAgents · Language models
- Omar KhattabDeveloper tools · Language models
- Junyang LinLanguage models · Agents
- Jay ParikhDeveloper tools · Agents
- Kari BriskiLanguage models · Agents
- David BauDeveloper tools · Language models
- Den DelimarskyDeveloper tools · Agents
- Shunyu YaoAgents · Language models
Suggest a correction or removal
Profiles cover public professional work only, and each statement cites a source. If something is out of date, missing or wrong, tell us and link a source. People can also ask for their profile to be corrected or removed.
References
7 sources · profile reviewed Oct 21, 2026 · data updated Oct 21, 2026
- About LangChain (company story)
- langchain-ai/langchain repository
- langchain-ai/langchain LICENSE (MIT)
- What does it mean to "own your intelligence"? (Harrison's In the Loop)
- langchain-ai/langchain initial commit (18aeb72)
- langchain-ai/deepagents repository (README, commits and MIT license)
- langchain-ai/langgraph repository (README and MIT license)