Heads up This site is currently under heavy development.
Subscribe Get it delivered — the daily firehose, filtered to the tools you run, plus the documentation changes vendors never announce. Compare plans →

The AI Toolchain — issue -295, October 26, 2025

THE AI TOOLCHAIN NO. -295
Tail
THE DAILY RELEASE FIREHOSE
PUBLISHED OCTOBER 26, 2025 · EVERY WEEKDAY
EDITIONS tail grep head diff uniq

The daily firehose — everything the toolchain shipped today, already filtered.

// HOW THIS ISSUE IS MADE

We read every release from the 174 tools on our watchlist at the source — GitHub and GitLab release notes, vendor release pages and changelogs, project blogs and feeds, vendor press releases, and the source code behind the tag. Bug-fix-only releases and non-product newsroom noise are dropped; what's left is summarized down to the new capability, how to try it, and any screenshots or videos the release itself published. Every entry links to the sources it was built from.

VIEW
ISSUE VIEW full issue
Do you prefer this view?
$ tct list   # 5 tools matched
AI & LLM Tooling
◆  AI Agent Frameworks

LlamaIndex

Sources Release notes → v0.14.6 NOTES

LlamaIndex v0.14.6 adds parallel tool calls, Isaacus and Helicone integrations, async Bedrock retriever, and GIN index support for PostgreSQL vector store.

└──▷ GET THIS VERSION
$ git clone --branch v0.14.6 https://github.com/run-llama/llama_index.git
# already have the repo? check out this version:
$ git checkout v0.14.6
└──▷ USE IT
Use the async Bedrock Knowledge Bases retriever to query Amazon Knowledge Bases in an async pipeline without blocking.
python
from llama_index.retrievers.bedrock import AmazonKnowledgeBasesRetriever

retriever = AmazonKnowledgeBasesRetriever(
    knowledge_base_id='<knowledge_base_id>',
    retrieval_config={'vectorSearchConfiguration': {'numberOfResults': 5}},
)
results = await retriever.aretrieve('What is our incident response policy?')
  • Adds allow_parallel_tool_calls parameter to non-streaming tool call support in llama-index-core.
  • Adds GIN index support for text array metadata in the PostgreSQL vector store (llama-index-vector-stores-postgres).
  • Adds async support for AmazonKnowledgeBasesRetriever in llama-index-retrievers-bedrock.
  • New llama-index-embeddings-isaacus integration (v0.1.0) adds Isaacus embeddings support.
  • New llama-index-llms-helicone integration (v0.1.0) adds Helicone LLM support.
+2 moreshow less
  • Adds GLM model support to llama-index-llms-baseten.
  • Updates OCI GenAI Cohere models in both llama-index-embeddings-oci-genai and llama-index-llms-oci-genai.
Was this useful?
◆  AI Coding Agents

SST OpenCode

Sources Release notes → v0.15.18 NOTES

The open source coding agent.

OpenCode v0.15.18 adds noReply parameter for response control and improves title generation reliability.

└──▷ GET THIS VERSION
$ git clone --branch v0.15.18 https://github.com/sst/opencode.git
# already have the repo? check out this version:
$ git checkout v0.15.18
  • Adds noReply parameter to control whether a response is returned.
  • Enables disabling of provider timeout via the timeout parameter.
Was this useful?

Alibaba Qwen Code

Sources Release notes → v0.1.0-nightly.20251026.2a5577e5 NOTES

Qwen Code v0.1.0-nightly ships a standalone bundled CLI package and syncs upstream Gemini-CLI v0.8.2 features.

└──▷ GET THIS VERSION
$ git clone --branch v0.1.0-nightly.20251026.2a5577e5 https://github.com/QwenLM/qwen-code.git
# already have the repo? check out this version:
$ git checkout v0.1.0-nightly.20251026.2a5577e5
  • Releases the qwen-code CLI as a standalone bundled package, enabling installation without separate dependency management.
  • Syncs upstream Gemini-CLI v0.8.2 changes into Qwen Code.
Was this useful?
◆  Local LLM Runtimes

SGLang

Sources Release notes → v0.5.4 NOTES

SGLang v0.5.4 adds overlap scheduler for speculative decoding, piecewise CUDA graph prefill, new model support, and ModelOpt quantization.

└──▷ GET THIS VERSION
$ git clone --branch v0.5.4 https://github.com/sgl-project/sglang.git
# already have the repo? check out this version:
$ git checkout v0.5.4
└──▷ TRY IT
Tokenize a prompt using the new OpenAI-compatible endpoint, useful for counting tokens before sending a generation request.
$ curl http://localhost:30000/tokenize -H 'Content-Type: application/json' -d '{"model": "<model>", "text": "Hello, world!"}'
  • Adds --sampling-defaults argument to the OAI serving chat interface to set server-wide sampling parameter defaults for ChatCompletionRequest.
  • Adds /tokenize and /detokenize OpenAI-compatible endpoints.
  • Adds reasoning and tool parser argument support in the router.
  • Adds IPv6 support across all router components.
  • Adds OpenAI router conversation API CRUD (create, retrieve, delete) for history management using conversation items.
+19 moreshow less
  • Adds get server info and get model info methods in the gRPC server.
  • Adds pipeline parallelism (PP) support for NIXL in prefill/decode disaggregation.
  • Adds prefix cache support for Qwen3 Next and GDN/Mamba models.
  • Adds native ModelOpt quantization support.
  • [beta] Adds overlap scheduler for speculative decoding.
  • [beta] Adds piecewise CUDA graph support for prefill.
  • Adds support for passing prefix keys for L3 store in HiCache.
  • Adds multi-item scoring with custom attention mask via the Generative Score API.
  • Adds MHA prefill support with FlashAttention 4.
  • Adds fullset optimizations for DeepSeek-V3.2 including MTP, PD disaggregation, and function calling.
  • Adds DGX Spark hardware support.
  • Adds KTransformer integration.
  • Adds LoRA support in the bench_serving OAI interface.
  • Adds float64 support to the moe_sum_reduce CUDA kernel.
  • Adds LongBench v2 evaluation utilities.
  • Adds various Blackwell kernel optimizations.
  • Adds manifest to versioned Docker releases.
  • Upgrades FlashInfer to 0.4.0.
  • Adds dedicated TOML configuration files for CPU and XPU targets.
└──▷ BREAKING ON UPGRADE
  • !The max_micro_batch_size argument is renamed to pp_max_micro_batch_size.
Was this useful?
Other / Uncategorized
◆  VECTOR DB RAG

Chroma

Sources Release notes → 1.2.2 NOTES

Chroma 1.2.2 ships a major Rust client expansion with new collection methods, BM25 support, and a chroma_cloud() constructor.

└──▷ GET THIS VERSION
$ git clone --branch 1.2.2 https://github.com/chroma-core/chroma.git
# already have the repo? check out this version:
$ git checkout 1.2.2
└──▷ USE IT
Connect to Chroma Cloud from Rust without manually constructing all client options.
rust
let client = ChromaHttpClient::new(ChromaClientOptions::chroma_cloud(
    "my-tenant-id",
    "my-api-key",
));
Fetch and then delete a collection by name using the new Rust client methods.
rust
let col = client.get_collection("threat-embeddings").await?;
client.delete_collection("threat-embeddings").await?;
  • Adds get_collection() and delete_collection() methods to the Rust client.
  • Adds collection.modify() method to the Rust client for updating collection properties.
  • Adds chroma_cloud() constructor for ChromaClientOptions to simplify connecting to Chroma Cloud from the Rust client.
  • Renames ChromaClient to ChromaHttpClient in the Rust client.
  • Renames config field default_database_name to database_name in the Rust client.
+12 moreshow less
  • Makes get_database_name() and get_tenant_id() public accessors on the Rust client.
  • Adds BM25 sparse retrieval support to the Rust client.
  • Adds Where clause serialization to the Rust client, enabling filtered queries.
  • Adds builder pattern for SearchPayload in the Rust client.
  • Adds schema helpers and Key object support to the Rust client schema API.
  • Supports From<pod> conversions for UpdateMetadataValue in the Rust client.
  • Exports top-level options and types from the chroma crate for easier downstream use.
  • Adds schema support (config -> schema on create_collection()) to the JavaScript client.
  • Adds query-string embedding support in the search API, enabling text queries without pre-embedding.
  • Adds SysDB functionality and a Rust task client with execution operators for TaskRunner support.
  • Adds stateful quota enforcement for the number of functions.
  • Controls how far into the future the s3heap scans, improving storage scheduling flexibility.
└──▷ BREAKING ON UPGRADE
  • !ChromaClient is renamed to ChromaHttpClient in the Rust client — any code referencing the old name will fail to compile.
  • !The default_database_name field in ChromaClientOptions is renamed to database_name — existing Rust client configurations using the old key will break.
  • !The config parameter on create_collection() is renamed to schema in the Rust client — call sites using the old name must be updated.
Was this useful?
my-toolchain — 0 tools
paste an install list to detect your tools

A brew list, a Brewfile, requirements.txt, a Dockerfile — or just the product names, free-form. Nothing leaves your browser.

    browse all tools →