True Foundry's open source AI agent harness True Forge boasts 30%-75% cheaper task completion than Claude Managed Agents | Venture Beat

Overview

True Foundry's open source AI agent harness True Forge boasts 30%-75% cheaper task completion than Claude Managed Agents

Another day, another new AI agent harness is released.

Details

Only this time, it's one that aims to solve a growing enterprise problem as AI agents proliferate: enabling greater developer control of agents and tools, while reducing cost.

True Foundry, a San Francisco B2B machine learning startup co-founded in 2021 by former Meta and Google engineers, has released its own custom True Forge harness under the permissive MIT License on Github. Thus, it can be used with any of a developer (or their parent enterprise's) preferred AI models, forked, modified, self-hosted and incorporated into commercial products.

The company states in a blog post that when it used True Forge paired with the open source GLM-5.2 LLM to successfully complete 11 of 14 tasks on Dev Rev’s Enterprise-Bench — testing multi-step tool use across CRM, issue tracking, and document management systems — it cost 75% less than achieving the same results with Anthropic's Claude Managed Agents harness powered by Claude Opus 4.8 (

2.90 compared to

11.80).

Using the same model in each harness, Opus 4.8, True Foundry still claims a cost savings of roughly 30% using True Forge compared to Claude Managed Agents (

8.50 vs

11.80).

Why is True Foundry giving this powerfully efficient harness away for free?

"We’ve had this ask from a bunch of customers," said Anuraag Gutgutia, True Foundry’s co-founder and COO, in an exclusive interview with Venture Beat. "You have an ability where you bring in agents and MCPs — can we also get something where you can actually launch these managed agents? I think that is the need we are satisfying. It is not a replacement. People will use this alongside other harnesses, like the cloud-managed ones or the commercial-provider-managed ones, but this will serve as a way for people to use them in a vendor-neutral way and also at a lower cost.”

Indeed, True Foundry already offers a paid "AI Gateway" for enterprises centrally controlling model and MCP access, credentials, permissions, budgets and observability. True Forge, by contrast, handles what happens above that gateway: the loop that lets a model repeatedly reason, call tools, receive results and continue working until a task is complete.

For enterprise developers, the practical proposition is that they can start locally with a single command and SQLite, then move the same agent harness into a shared deployment using Docker Compose or Helm with Postgres and Redis.

True Foundry explicitly warns that the local configuration is intended only for use on a developer’s machine, not as an internet-facing production service.

Gutgutia said the company ultimately wants its AI Gateway to become the common layer beneath whichever agents and harnesses an enterprise chooses.

“There will be a set of companies that will use our harness as the way to launch managed agents,” he said, while others may continue using Claude, other open-source harnesses or internal systems. “But all that traffic should still be flowing through our gateway.”

Context management is where True Forge tries to cut waste

True Forge’s architecture centers on context engineering — controlling how much information gets sent back into the model on every step of an agent run.

That includes delaying the loading of MCP tool schemas until they are needed, delegating isolated tasks to subagents, moving oversized tool results into files instead of stuffing them into the active context window, processing structured results through code, and automatically compacting long-running conversations.

The documentation sets the default compaction threshold at 50,000 tokens, though it can be changed per agent.

True Forge also treats the sandbox differently from runtimes that keep an agent inside an isolated environment throughout its run. The core agent loop remains on the True Forge server; a sandbox is provisioned as a tool only when the agent needs to execute code or work with files. True Foundry says that reduces unnecessary compute and allows a server to run more agents concurrently.

The company argues those choices directly reduce model spending.

How True Forge compares to Claude Managed Agents and other leading orchestration harnesses

True Foundry True Forge: General-purpose production agent harness designed for enterprise deployments.

Deep Seek Harness: Open-source agent harness, currently positioned as a developer preview.

Open AI Codex CLI: Coding-focused agent harness designed primarily for software-engineering workflows.

Lang Chain Deep Agents: General-purpose agent harness built on Lang Graph.

Anthropic Claude Managed Agents: Fully managed production agent runtime operated by Anthropic.

True Foundry True Forge: The open-source harness itself is free. Model, sandbox and infrastructure costs are separate. True Foundry also offers an optional commercial governance layer through its broader platform.

Deep Seek Harness: No harness license fee. Users separately pay for whatever model providers and infrastructure they use.

Open AI Codex CLI: The CLI is open source. Underlying model/API or subscription costs are separate, Open AI says around

100–

200 per developer per month, although actual spending varies substantially with model choice

Open AI Codex CLI: The CLI is open source. Underlying model/API or subscription costs are separate, Open AI says around

100–

200 per developer per month, although actual spending varies substantially with model choice

Lang Chain Deep Agents: Open source, with model and infrastructure expenses separate. Lang Chain also offers optional commercial services through Lang Smith.

Anthropic Claude Managed Agents: Claude tokens consumed plus $0.08 per running session-hour, with runtime metered to the millisecond.

True Foundry True Forge: Vendor-neutral and designed around bring-your-own-model support.

Deep Seek Harness: Multi-provider and not restricted to Deep Seek models.

Open AI Codex CLI: Supports configurable inference endpoints, including Open AI-compatible services and local-model options.

Lang Chain Deep Agents: Broad multi-provider support through the Lang Chain ecosystem.

True Foundry True Forge: Can run locally as a single process with SQLite, then move into a production deployment using Docker Compose or Helm with Postgres and Redis.

Deep Seek Harness: Designed for local or self-hosted operation.

Open AI Codex CLI: Primarily a local CLI experience, alongside Open AI-hosted Codex products and services.

Lang Chain Deep Agents: Can be self-hosted or deployed through Lang Chain and Lang Smith infrastructure.

Anthropic Claude Managed Agents: Anthropic manages the runtime and infrastructure.

True Foundry True Forge: MCP and tool orchestration, subagents, human approval checkpoints, persistent sessions, context compaction, large-result offloading, Code Mode, generative UI, tracing and a sandbox-as-a-tool architecture.

Deep Seek Harness: Pluggable models, tools, session storage and agent loops, along with sandboxing, permissions, approval gates and skills.

Open AI Codex CLI: Agent loop, repository and file operations, shell execution, MCP tools, sandboxing, permissions, approvals and context management.

Lang Chain Deep Agents: Planning, subagents, skills, filesystem-based context management, persistent memory, human-in-the-loop controls, MCP support and multiple sandbox backends.

Anthropic Claude Managed Agents: Managed execution environments, persistence, tools, sandboxing and infrastructure for long-running agents.

True Foundry True Forge: Its strongest distinction is the combination of an open-source, vendor-neutral harness with a clear path from local development to a shared production runtime, plus an optional enterprise governance plane through True Foundry.

Deep Seek Harness: Emphasizes deep modularity. Major parts of the runtime, including models, tools, storage and the agent loop, are designed to be replaceable plugins.

Open AI Codex CLI: Stands out as a highly developed software-engineering-specific harness rather than a general-purpose enterprise agent server.

Lang Chain Deep Agents: Benefits from the broader Lang Chain and Lang Graph ecosystem and offers a mature open-source path for building general-purpose agents.

Anthropic Claude Managed Agents: Minimizes operational burden by having Anthropic manage the runtime, but trades that convenience for tighter model and platform coupling.

Open source does not automatically mean governed

For enterprise buyers, one of the most important distinctions is between True Forge by itself and True Forge connected to True Foundry’s commercial AI Gateway.

The open-source harness can run independently. But it does not magically inherit an organization’s enterprise access policies on its own.

“If you are using just the open source version of our agent harness, yes, you will need to put the right controls therein or in front of some other internal control system,” Gutgutia told Venture Beat.

When paired with True Foundry’s gateway, the company says agents can inherit the identities and access controls already attached to models, MCP servers, tools, skills and other agents. Gutgutia described the gateway as the place where enterprise SSO, identity providers and granular permissions can be centrally enforced rather than reimplemented separately for every agent.

That distinction is likely to be important for platform engineering teams evaluating the project. True Forge is free software; True Foundry’s governance layer is the commercial control plane around it.

True Foundry says Net App was a beta user of the harness and contributed requirements during development. Gutgutia said Net App’s IT organization has used the technology for incident response and faster ticket triage, while also exposing internal agents as self-service tools for developers. He also identified Automattic as an early user.

Background on True Foundry and its business to date

True Foundry was founded in 2021 to help enterprises deploy and operate machine-learning models, including Kubernetes-based model serving, training and infrastructure management.

Its three co-founders — Nikunj Bajaj, Abhishek Choudhary and Anuraag Gutgutia — previously worked at Meta and World Quant, respectively.

Gutgutia said the founders' common experience was working around mature systems where infrastructure and controls were designed to prevent costly mistakes — an idea they believed would become increasingly important as AI moved into production inside large companies.

As generative AI spread through enterprise software, True Foundry expanded from that MLOps foundation toward managing LLM applications and, increasingly, the models, tools and agents around them.

By 2025, the company had made its AI Gateway a central part of the business: a layer sitting between enterprise applications and model providers that handles routing, authentication, access controls, observability, budgets, guardrails and failover.

That evolution has been backed by roughly

21 million in outside financing. True Foundry raised a

19 million Series A in February 2025 led by Intel Capital, with participation from existing investors Eniac Ventures and Peak XV's Surge, as well as Jump Capital and angel investors including Gokul Rajaram and Mohit Aron. The round brought total financing to about $21 million, according to Intel Capital's announcement.

At the time, True Foundry said its customer base had grown fourfold year over year and that it was managing more than 1,000 clusters for machine-learning workloads.

The business has since become increasingly oriented around large-scale enterprise AI traffic. In Venture Beat's January 2026 coverage of True Foundry's True Failover launch, the company said it had more than 30 paid customers worldwide, had exceeded $1.5 million in annual recurring revenue during the prior year and was processing more than 10 billion requests per month through its AI Gateway.

Customers and deployments cited by True Foundry have included Net App, Siemens Healthineers, Res Med, Automation Anywhere, Nvidia, Games 24x 7 and others; Gutgutia also named Net App, Siemens, Synopsys and Automation Anywhere among Fortune 1000 organizations working with the company in his interview with Venture Beat.

True Foundry has also been expanding through acquisition. In June 2026 it acquired UK-based Seldon AI, a longtime MLOps vendor whose Seldon Core software has been used for production model serving and inference.

As the acquisition shows, rather than treating traditional ML, LLMs, tools and agents as separate infrastructure categories, True Foundry is trying to put them behind a common deployment and governance layer.

True Forge extends that strategy upward into the agent runtime itself. Until now, True Foundry's commercial center of gravity has largely been the control plane underneath enterprise AI workloads — deciding which users and applications can access which models and tools, routing requests, enforcing policy, monitoring spend and keeping services available.

True Forge gives the company an open-source runtime above that layer where agents can actually execute. Gutgutia described the relationship as complementary: organizations can run True Forge independently or continue using other agent harnesses, while True Foundry's longer-term business opportunity is to provide the common governance and infrastructure underneath whichever agents enterprises choose.

Key Takeaways

True Foundry's open source AI agent harness True Forge boasts 30%-75% cheaper task completion than Claude Managed Agents
Another day, another new AI agent harness is released
Only this time, it's one that aims to solve a growing enterprise problem as AI agents proliferate: enabling greater developer control of agents and tools, while reducing cost
True Foundry, a San Francisco B2B machine learning startup co-founded in 2021 by former Meta and Google engineers, has released its own custom True Forge harness under the permissive MIT License on Github
The company states in a blog post that when it used True Forge paired with the open source GLM-5

TrueFoundry's open source AI agent harness TrueForge boasts 30%-75% cheaper task completion than Claude Managed Agents | VentureBeat

True Foundry's open source AI agent harness True Forge boasts 30%-75% cheaper task completion than Claude Managed Agents | Venture Beat

Overview

True Foundry's open source AI agent harness True Forge boasts 30%-75% cheaper task completion than Claude Managed Agents

Details

Context management is where True Forge tries to cut waste

How True Forge compares to Claude Managed Agents and other leading orchestration harnesses

Open source does not automatically mean governed

Background on True Foundry and its business to date

Key Takeaways

True Foundry's open source AI agent harness True Forge boasts 30%-75% cheaper task completion than Claude Managed Agents

Cut Costs with Runable

Which apps do you use?

Apps to replace

TrueFoundry's open source AI agent harness TrueForge boasts 30%-75% cheaper task completion than Claude Managed Agents | VentureBeat

True Foundry's open source AI agent harness True Forge boasts 30%-75% cheaper task completion than Claude Managed Agents | Venture Beat

Overview

True Foundry's open source AI agent harness True Forge boasts 30%-75% cheaper task completion than Claude Managed Agents

Details

Context management is where True Forge tries to cut waste

How True Forge compares to Claude Managed Agents and other leading orchestration harnesses

Open source does not automatically mean governed

Background on True Foundry and its business to date

Key Takeaways

True Foundry's open source AI agent harness True Forge boasts 30%-75% cheaper task completion than Claude Managed Agents

Cut Costs with Runable

Which apps do you use?

Apps to replace

Does giving a camera wings dodge the FCC’s drone ban? | The Verge