Log inSign up
TrueFoundry
395 posts
TrueFoundry profile banner
@truefoundry

TrueFoundry

@truefoundry
TrueFoundry is a unified platform with an enterprise-grade AI Gateway - combining LLM, MCP, and Agent Gateway to securely manage, route, and govern AI workloads
San Francisco
truefoundry.com
Joined April 2022
57
Following
1,154
Followers
RepliesRepliesRepostsRepostsMediaMediaArticlesArticles

Log in or sign up for X

See what’s happening and join the conversation

Continue with phone
or
Log in with username or email
Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
  • Pinned
    @truefoundry
    TrueFoundry
    @truefoundry
    Aug 19
    Article cover image
    Article
    The Agent Harness Should Be Open
    Today, we are open sourcing TrueForge, the agent harness we use at TrueFoundry to build and run general-purpose agents. Because once agents do real work, the harness shapes context, tool use,...
    56
  • @truefoundry
    TrueFoundry
    @truefoundry
    6h
    Article cover image
    Article
    We cut model costs 69% by routing requests on complexity. Here's the data.
    We just released Auto Routing on the TrueFoundry AI Gateway. It reads each incoming request, scores how hard it is, and sends it to the model you assigned to that level of difficulty. You define three...
  • @truefoundry
    TrueFoundry
    @truefoundry
    Sep 8
    Install to working agent in 8 minutes - on a model running on your own hardware. one npx command. one SQLite file. @dr_cintas built the whole thing and filmed it 👇
    @dr_cintas
    Alvaro Cintas
    @dr_cintas
    Sep 8
    run agent harnesses on local models. (no token costs, no model API keys, 100% open-source) your agent runs on your machine. the model doesn't. every prompt, every file, and every secret leaves your laptop before the agent does anything with it. this new open-source fixes that.
    Image
    00:00
  • @truefoundry
    TrueFoundry
    @truefoundry
    Sep 7
    "AGI has arrived" claims Jensen Huang (NVIDIA) . True or not, models keep getting more autonomous. Even OpenAI ships Astra in phases, cyber capabilities gated. Capability isn't the bottleneck for agents anymore - control is. Approvals, sandboxes, traces. That's the harness layer.
    @JensenHuang
    Jensen Huang
    NVIDIA
    @JensenHuang
    Sep 6
    Replying to @ChaseLochmiller and @OpenAI
    GPT-6 Astra, trained on ~100K+ NVIDIA Grace Blackwell NVLink72. From ChatGPT to o1 to Astra in 4 years. AGI has arrived. Congratulations @OpenAI team. 400K GPUs coming online next.
  • @truefoundry
    TrueFoundry
    @truefoundry
    Sep 4
    This is the whole pitch for an agent harness in 60 seconds: the report is only as current as the tools you gave it. Built on TrueForge, open source. Thanks @TechWithTimm for trying it out !
    @TechWithTimm
    Tech With Tim
    @TechWithTimm
    Sep 4
    How I built an open-source AI research agent
    Image
    00:00
Advertisement
Advertisement