- Load a skill’s tools only when the skill is read.
- Reset stale encoding when overwriting text.
- dcba425 release(deepagents): 0.7.22
- 337f4d0 chore(deps): raise dependency minimums for all
- 92cd8e7 feat(sdk): load a skill's tools only when the skill is read
- fb62fb06 fix(sdk): reset stale encoding on text overwrite
Deep Agents by LangChain
Overview
A batteries-included agent harness built on LangGraph, with planning, a virtual file system and sub-agents for long-running tasks.
Deep Agents was downloaded 2M times from npm and PyPI in the week ending Oct 4, 2026, up 13.5% on the week before and up 5.0% over the last 30 days compared with the 30 before. The GitHub repository has 30K stars, 988 of them added in the last 30 days. The latest stable release is 0.7.22, published Oct 5, 2026; there were 29 stable releases in the past 30 days. On Terminal-Bench 2.0 its best listed result is 66.5% with GPT-5.2-Codex, ranking 22 of 43 agents on that board. It was mentioned in 15 Hacker News posts and comments over the last 30 days.
Deep Agents usage and attention over time
Download the raw daily series: deepagents.csv
Install Deep Agents
| npm | npm install deepagents |
|---|---|
| PyPI | pip install deepagents |
These commands use the packages tracked on this page. The vendor may recommend a different installer; see the official documentation.
Key facts
| Maker | LangChain |
|---|---|
| Type | Agent harness |
| License | MIT |
| Interfaces | Python library, JavaScript library |
| Main language | Python |
| Open issues and PRs | 199 |
Pricing
Deep Agents is open source and free to use; you pay only for the models and infrastructure it runs on.
, checked Oct 5, 2026. Prices change often; confirm before you buy.
Pulse Score breakdown
Each component is scored 0 to 100 from public signals; a dash means no data for it. Methodology.
What changed: recent Deep Agents releases
- Emit a cacheexpiring hook before the prompt cache expires (#6638).
- Keep the transcript at its current position when opening pickers (#6635).
- Share cache-expiring notifications with the TUI (#6639).
- Use listed skill paths instead of inferring their locations (#6711).
- Correct product and command names in skill guides (#6637).
- e4c1ffe release(deepagents-code): 0.1.80
- Add a Slack channel adapter, with support for outbound user mentions. (#6575,
- Add sender pairing for DM access and Slack, including DM delivery of pairing codes for Slack mentions. Paired senders are admitted in every chat. (#6579, #6582, #6584,
- Add /model for per-chat model switching.
- Add cron expressions and until expiry for scheduled jobs, run their subagents inline, and deliver results from thread-based jobs to the channel by default. (#6526, #6425,
- Add opt-in sandboxed execution via DEEPAGENTSTALONSANDBOX.
- Register chat commands as Discord slash commands and share public thread history by guild channel. (#6303,
- FilesystemMiddleware can now store blobs on the backend (#6550).
- 4394bcd release(deepagents): 0.7.21
- e38e6c9 feat(sdk): allow FilesystemMiddleware to store blobs on backend
- c2da83e build(deps): bump urllib3 from 2.7.0 to 2.8.0 in /libs/deepagents
- c9b2ce1 chore(deps): raise dependency minimums for all
- MCP tool calls now use configurable timeouts to prevent them from hanging indefinitely (#6625).
- Stdio MCP servers now start in the session directory (#6626).
- JavaScript subagent costs are preserved when resuming a session (#6433).
- Thread switching now completes its preflight faster and shows progress sooner (#6607).
- The /effort setting is now constrained for between-tools thinking (#6630).
- CLI help now displays the same defaults used at runtime (#6613).
- Fixed binary content in StateBackend.uploadfiles being tagged as base64.
- 6bf7802 release(deepagents): 0.7.20
- a87e219 chore(deps): raise dependency minimums for all
- 689898e chore(deps): raise dependency minimums for all
- b1ebc5b fix(sdk): tag binary StateBackend.uploadfiles content as base64
- 512334f chore(deps): raise dependency minimums for all
Deep Agents benchmark results
| Benchmark | Model | Effort | Tasks solved | Cost of run | Place |
|---|---|---|---|---|---|
| Terminal-Bench 2.0 | GPT-5.2-Codex · v0.0.1 | — | 66.5% ± 3.1 | — | #22 of 43 |
Up to four best runs per board. Scores are not comparable between Terminal-Bench versions. Source: Terminal-Bench (tbench.ai).
Deep Agents alternatives
| # | Agent | Pulse | Downloads 7d | 7d | 30d | VS Code installs | Stars | Latest release | Price | Last 90 days | |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 4 |
LangChainLangChain |
77 | 44.3M | up 1.9% | down 22.0% | — | 147K+45/day | 1.4.38d ago | Free (OSS) | ||
| 10 |
LangGraphLangChain |
69 | 16.1M | up 11.4% | down 21.8% | — | 42.7K+48/day | 1.2.13yesterday | Free (OSS) | ||
| 11 |
AI SDKVercel |
67 | 34.5M | up 13.5% | up 20.9% | — | 27.1K+18/day | 6.0.301yesterday | Free (OSS) | ||
| 13 | 63 | 8.7M | up 0.6% | up 2.0% | — | 8,679+23/day | 1.58.0yesterday | Free (OSS) | |||
| 17 |
Claude Agent SDKAnthropic |
59 | 21.5M | up 14.6% | up 0.6% | — | 8,219+5/day | 0.2.1636d ago | Free (OSS) | ||
| 21 |
MastraMastra |
58 | 2.2M | up 11.1% | up 19.1% | — | 28.6K+27/day | 1.74.0yesterday | Free (OSS) | ||
| No agents match that filter. | |||||||||||
Head to head: Deep Agents vs LangGraph
Deep Agents FAQ
How much does Deep Agents cost?
Deep Agents is open source and free to use; you pay only for the models and infrastructure it runs on.
Is Deep Agents open source?
Yes. Deep Agents is open source, released under the MIT license.
How popular is Deep Agents?
Deep Agents was downloaded 2M times from npm and PyPI in the week ending Oct 4, 2026, up 13.5% on the week before and up 5.0% over the last 30 days compared with the 30 before. The GitHub repository has 30K stars, 988 of them added in the last 30 days. The latest stable release is 0.7.22, published Oct 5, 2026; there were 29 stable releases in the past 30 days.
What is the latest version of Deep Agents?
The latest stable release we track is 0.7.22, published on Oct 5, 2026.
What are the alternatives to Deep Agents?
The closest alternatives in the same category by Pulse Score are LangChain, LangGraph, AI SDK, Strands Agents.
Where these numbers come from
npm: deepagents. PyPI: deepagents. GitHub: langchain-ai/deepagents. See data sources for how each one is collected.
