--- title: TrueFoundry debuts open-source AI agent harness,... description: TrueFoundry launched TrueForge, an open-source AI agent harness that runs on an enterprise's own infrastructure and supports OpenAI, Anthropic, and 20+ other... canonical: https://daily.dev/posts/truefoundry-debuts-open-source-ai-agent-harness-claiming-up-to-75-lower-costs-ubfmgdpsw twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: TrueFoundry debuts open-source AI agent harness, claiming up to 75% lower costs | daily.dev og:description: TrueFoundry launched TrueForge, an open-source AI agent harness that runs on an enterprise's own infrastructure and supports OpenAI, Anthropic, and 20+ other... og:url: https://daily.dev/posts/truefoundry-debuts-open-source-ai-agent-harness-claiming-up-to-75-lower-costs-ubfmgdpsw og:image: https://api.daily.dev/og/posts/UBfMGdpsW.png og:image:alt: TrueFoundry debuts open-source AI agent harness, claiming up to 75% lower costs og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # TrueFoundry debuts open-source AI agent harness, claiming up to 75% lower costs **[InfoWorld](https://daily.dev/sources/infoworld)** · 4 min read · 0 upvotes · 0 comments ## Summary TrueFoundry launched TrueForge, an open-source AI agent harness that runs on an enterprise's own infrastructure and supports OpenAI, Anthropic, and 20+ other models, positioning it against Anthropic's hosted Claude Managed Agents. TrueFoundry claims up to 75% lower operating costs in its own benchmark: on a 14-task DevRev Enterprise-Bench test, TrueForge with Anthropic's Opus 4.8 averaged $8.50 per run versus $11.80 for Claude Managed Agents (30% less), while TrueForge running GLM-5.2 averaged $2.90 per run for similar task completion (roughly 75% less). Analysts note the self-run benchmark lacks independent validation, and that self-hosting tends to pay off for high-volume, continuous workloads or regulated industries needing custom governance, while managed services may stay cheaper for smaller or unpredictable workloads. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is TrueForge and how does it compare to Anthropic's Claude Managed Agents? TrueForge is an open-source AI agent harness from TrueFoundry that runs on an enterprise's own infrastructure and supports OpenAI, Anthropic, and more than 20 other models, letting developers bring their own MCP servers and API keys. It competes with Claude Managed Agents, Anthropic's hosted agent runtime for the Claude Platform, by offering model flexibility and avoiding vendor lock-in, plus a hosted usage-based pricing option. _Compare emerging agent harness options like TrueForge on daily.dev before locking into a managed agent runtime._ ### How much cheaper is TrueForge than Claude Managed Agents according to TrueFoundry's benchmark? In a 14-task DevRev Enterprise-Bench test, TrueForge using Anthropic's Opus 4.8 averaged $8.50 per run versus $11.80 for Claude Managed Agents, about 30% less while completing a similar number of tasks. Switching TrueForge to GLM-5.2 dropped the average to $2.90 per run for comparable task completion, roughly a 75% reduction. TrueFoundry ran the benchmark itself, so results are not yet independently validated at production scale. _Track independent validation of agent cost benchmarks like this on daily.dev before budgeting for a switch._ ### When does self-hosting an AI agent runtime pay off compared to using a managed service? Self-hosting tends to pay off for high-volume agents used continuously, where enterprises can route workloads across cheaper open-weight models and already have infrastructure and engineering expertise to run them, according to industry analysts. For smaller or unpredictable workloads, managed services can remain cheaper since the provider absorbs infrastructure and operational overhead. Token consumption is typically the largest share of agent operating costs either way. _Weigh self-hosted versus managed agent runtimes for your workload using cost breakdowns shared on daily.dev._ ## Similar posts on daily.dev - [Anthropic, OpenAI, Google, and Microsoft agree that the harness is the product. They disagree on the price.](https://daily.dev/posts/anthropic-openai-google-and-microsoft-agree-that-the-harness-is-the-product-they-disagree-on-the-hvk3m7gts) · The New Stack · 1 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#mcp](https://daily.dev/tags/mcp), [#claude](https://daily.dev/tags/claude) [View this post on daily.dev](https://daily.dev/posts/truefoundry-debuts-open-source-ai-agent-harness-claiming-up-to-75-lower-costs-ubfmgdpsw) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"TrueFoundry debuts open-source AI agent harness, claiming up to 75% lower costs","url":"https://daily.dev/posts/truefoundry-debuts-open-source-ai-agent-harness-claiming-up-to-75-lower-costs-ubfmgdpsw","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/truefoundry-debuts-open-source-ai-agent-harness-claiming-up-to-75-lower-costs-ubfmgdpsw"},"datePublished":"2026-08-20T12:47:34.855Z","dateModified":"2026-08-20T12:48:35.139Z","description":"TrueFoundry launched TrueForge, an open-source AI agent harness that runs on an enterprise's own infrastructure and supports OpenAI, Anthropic, and 20+ other...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/cee4b31e0365d4904a2ac2eaf273e80b?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/cee4b31e0365d4904a2ac2eaf273e80b?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"InfoWorld","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"InfoWorld","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/bf6d68a999064029b0bb09aa6268f1f3","url":"https://daily.dev/sources/infoworld"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/truefoundry-debuts-open-source-ai-agent-harness-claiming-up-to-75-lower-costs-ubfmgdpsw","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,mcp,claude","timeRequired":"PT4M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"InfoWorld","item":"https://daily.dev/sources/infoworld"},{"@type":"ListItem","position":3,"name":"TrueFoundry debuts open-source AI agent harness, claiming up to 75% lower costs"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/truefoundry-debuts-open-source-ai-agent-harness-claiming-up-to-75-lower-costs-ubfmgdpsw#faq","mainEntity":[{"@type":"Question","name":"What is TrueForge and how does it compare to Anthropic's Claude Managed Agents?","acceptedAnswer":{"@type":"Answer","text":"TrueForge is an open-source AI agent harness from TrueFoundry that runs on an enterprise's own infrastructure and supports OpenAI, Anthropic, and more than 20 other models, letting developers bring their own MCP servers and API keys. It competes with Claude Managed Agents, Anthropic's hosted agent runtime for the Claude Platform, by offering model flexibility and avoiding vendor lock-in, plus a hosted usage-based pricing option. Compare emerging agent harness options like TrueForge on daily.dev before locking into a managed agent runtime."}},{"@type":"Question","name":"How much cheaper is TrueForge than Claude Managed Agents according to TrueFoundry's benchmark?","acceptedAnswer":{"@type":"Answer","text":"In a 14-task DevRev Enterprise-Bench test, TrueForge using Anthropic's Opus 4.8 averaged $8.50 per run versus $11.80 for Claude Managed Agents, about 30% less while completing a similar number of tasks. Switching TrueForge to GLM-5.2 dropped the average to $2.90 per run for comparable task completion, roughly a 75% reduction. TrueFoundry ran the benchmark itself, so results are not yet independently validated at production scale. Track independent validation of agent cost benchmarks like this on daily.dev before budgeting for a switch."}},{"@type":"Question","name":"When does self-hosting an AI agent runtime pay off compared to using a managed service?","acceptedAnswer":{"@type":"Answer","text":"Self-hosting tends to pay off for high-volume agents used continuously, where enterprises can route workloads across cheaper open-weight models and already have infrastructure and engineering expertise to run them, according to industry analysts. For smaller or unpredictable workloads, managed services can remain cheaper since the provider absorbs infrastructure and operational overhead. Token consumption is typically the largest share of agent operating costs either way. Weigh self-hosted versus managed agent runtimes for your workload using cost breakdowns shared on daily.dev."}}]} ```