BFE Files

A modern layer 7 load balancer from baidu

This is an exact mirror of the BFE project, hosted at https://github.com/bfenetworks/bfe. SourceForge is not affiliated with BFE.

The interactive file manager requires Javascript. Please enable it or use sftp or scp.
You may still browse the files here.

Name	Modified	Size	InfoDownloads / Week
Parent folder
bfe_1.8.5_windows_amd64.tar.gz	2026-08-21	19.8 MB	1
bfe_1.8.5_linux_arm64.tar.gz	2026-08-21	18.3 MB	0
bfe_1.8.5_linux_amd64.tar.gz	2026-08-21	19.9 MB	0
bfe_1.8.5_darwin_amd64.tar.gz	2026-08-21	20.3 MB	0
BFE v1.8.5 source code.tar.gz	2026-08-21	6.6 MB	0
BFE v1.8.5 source code.zip	2026-08-21	10.1 MB	0
README.md	2026-08-21	1.6 kB	1
Totals: 7 Items		95.0 MB	2

[v1.8.5] - 2026-08-21

Added

Add multi-API-Key support for AI backend clusters (Pull [#1314])
Add RMB quota support in mod_ai_token_auth (Pull [#1314])
Add key_id field for API-Key token in access logs (Pull [#1318])
Add provider/model prefix routing support (Pull [#1315])
Add req_body_json_prefix_in condition primitive (Pull [#1314])
Adapt bfe-access-pb v0.2.0 AI observability fields in access logs (Pull [#1321])
Support body rewind when fallback (Pull [#1313])
Add AccessibleBodySize config in bfe.conf (Pull [#1313])
Monitor and limit TotalBodyBufferSize (Pull [#1313])

Changed

Trigger cluster-level fallback on 4xx status codes (Pull [#1318])
Merge multiple AI model body rewrites into one (Pull [#1321])

Fixed

Fix ai token auth default rule path (Pull [#1251])
Fix RMB cost calculation at request finish for streaming responses (Pull [#1318])
Fix log messages (Pull [#1313])

Source: README.md, updated 2026-08-21

Other Useful Business Software

Build Agents and Models on One Platform Icon

Build Agents and Models on One Platform

Everything you need to build production-ready agents and models. Access 200+ Google and third-party AI models and tools.

Gemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.

Start Free

Custom VMs From 1 to 96 vCPUs With 99.95% Uptime Icon

Custom VMs From 1 to 96 vCPUs With 99.95% Uptime

General-purpose, compute-optimized, or GPU/TPU-accelerated. Built to your exact specs.

Live migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.

Start Free

Build Agents and Models on One Platform

Everything you need to build production-ready agents and models. Access 200+ Google and third-party AI models and tools.

Gemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.

Start Free

Recommended Projects

CoreDNS
CoreDNS is a DNS server that chains plugins
Elastica
Elastica is a highly efficient and extensible, rules-based load-balancer for JBoss that adds dynamic behavior to EJB load balancing. Rules can be defined to redirect EJB requests according to request data, server performance data, or even the time of day
GoProxy
High performance proxy server implemented by golang
RELIANOID
Network Load Balancer and Application Security
Octopus Load Balancer
Octopus Load Balancer is an extremely fast TCP load balancer with extensions for HTTP to allow balancing based on URI. Features include: server health checks and load polling, dynamic configuration, and the ability to carbon copy incoming requests.