context
60 stories and discussions about context, aggregated from every source we track.
A collaborative AI workspace, built on your company context. Build and orchestrate agents right alongside your team's projects, meetings, and connected apps.
<p>Additional context: <a href="https://www.youtube.com/watch?v=M1si1y5lvkk" rel="ugc">https://www.youtube.com/watch?v=M1si1y5lvkk</a></p> <p>No abstract.</p>
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
All of these updates are in Servo 0.0.3.
<p>Context: I'm the author of the Rust patch</p>
Most engineering teams working on long-context agents hit the same billing wall around turn twenty. A...
The UI: An example output: # Project...
Open Model Context Protocol (omcp) — a community-driven hard fork. Build without permission. - enclawed/omcp
Eliminating the widget builder tax, closure fatigue, and the context.watch trap in Flutter: how 1:1 symmetry between containers and BuildContext unlocks cleaner, faster reactive apps.
Message your team and AI agents in one place. Praxos lets people and agents talk, share work, and get things done together.
High-assurance in-memory Tree-Sitter AST context firewall and pruning MCP server for coding agents (-72.4% token mass). - heuristicolab/ctxfw
Having to manually copy-paste context between your code environments (like IDEs) and Claude Desktop,...
This is a submission for the Sanity Challenge, Path Two: Build a Knowledge Base or Context...
Model Context Protocol has changed the way AI applications interact with external tools. Instead of...
Context, limitations, and evaluation criteria for OliverDB performance results.
Technology, startups, programming, technical management and software architecture
We introduce Context Language Models (CLMs), language models that natively manage their own context. We implement this by treating the context as a file and allowing the model to make unrestricted updates to this file.…
How a tree of business domains makes analytics context easier to debug, maintain, and retrieve without overloading the agent.
Most developers still treat prompt injection as a leakage problem. Someone types an adversarial...
Model-requested semantic context compaction for Codex, with complete checkpoints and no per-turn cap. - manuelcecchetto/codex-context-gc
At some point in growing a large-scale software system, you’ll require “out of band” context: data which is not explicitly passed as an argument to a function but rather implicitly attached to the request, job or event…
This author has chosen to make their posts visible only to people who are signed in.
For the folks who found this blog from Anthropic’s site, welcome! For everyone else, I’d better give some context. Last month, I had a blog post titled “It Only Counts When AI Get…
Compare GPT-6 Sol and Luna pricing, context limits, reasoning, and use cases to choose a model for coding or high-volume applications.
🛠️ toolhub - Turn ANY console script into an LLM tool in 2 seconds. Lightweight, self-hosted, tree-structured alternative to MCP & LangChain. - Talos-popcorn/toolhub
Here's a chat someone thought you'd want to see.
A semantic layer is a governed catalog of definitions that sits on top of your existing data and tells agents and people what to trust. Here's how we built one into PostHog's context warehouse.
Heimr 570M is a 2.7B-parameter, 570M-active hybrid of Mamba-3 and Heimr attention with mixture-of-experts layers, built for phones and laptops. Its decode throughput and memory stay nearly flat to 64K tokens of…
Jev reads the message, Gradium Voice Design gives the agent a voice that fits. Every step on the critical path is traced.
A lot of prior work addressed key-value (KV) cache selection and compression by sparse attention to enable long-context inference for transformer language models without excessive hardware budgets. We provide a new…
Read-only Postgres MCP server: a drop-in replacement for the archived server-postgres, with schema context for correct answers. - contextflo/postgres-mcp
The first frontier LLM with ten million tokens of context.
LLM coding agents operate by constructing trajectories that accumulate reasoning, tool calls, and results to enable multi-step decision-making. However, the conventional append-only trajectory architecture found in…
Make decisions from the command line, in scripts, and in agent skills. No code required. - vsekhar/decide
Why LLMs changed what we expect from monitoring, and why centralized, queryable context makes every alert investigable.
Large language model (LLM) agents often handle streams of related tasks, yet standard harnesses repeatedly ask the model to reconstruct the same control decisions inside each task's context. We study whether task…
A collaborative AI workspace, built on your company context. Build and orchestrate agents right alongside your team's projects, meetings, and connected apps.
A Model Context Protocol (MCP) server for NATS messaging system integration - sinadarbouy/mcp-nats
The official field manual for wb-flow: a zero-dependency CLI that bootstraps agentic AI workflows into any repo.
An analytical database built for agents to use directly: columnar storage, a vectorized query engine, and MCP as a first-class interface - sivsivsree/agedb
An architectural deep dive into why baking planning directly into the agent runtime prevents context drift, eliminates expensive 100k-1M token compaction passes, slashes multi-agent FinOps costs, and preserves prompt…
FreshThread BETA version: downloads, release notes and bug reports. Application source is maintained separately. - GG95-lab/FreshThread-BETA-version
Vision Language Models (VLMs) offer the exciting possibility of processing text as rendered images, bypassing the need for tokenizing the text into long token sequences. Since VLM image encoders map fixed-size images…
vsql-mcp puts a Model Context Protocol server inside VillageSQL Server, so AI agents can browse MySQL schema and run governed, read-only queries
Serve analytics agents with context that stays in sync as schemas and business logic change. Every update is tested, reviewed, and approved.
The Postman for MCP. Contribute to BraveRam/postmcp development by creating an account on GitHub.
Turn context into structured decisions with open language models. Try Simple Jev's live classifier demo, explore the API, and train a model for your task.
slivingdoc is an MCP server that gives agents one shared directory of notes, merged with Git semantics and stored durably in S3.
From “Storing” to “Staying Current”: Why Agent Memory Needs a Shared Evaluation
We ran three context-compaction strategies through the same 178-question exam. FutureOS kept 83% of the values that had been compacted away; OpenCode kept 47%, Codex 38%. The difference isn't a better summary — it's…
Stack instructions, documents and memories. Clear rows to answer tasks. Try not to drown in verbose logs.
This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content. ...
RAG fixes what the model reads before it sees the question. Jev fixes what the model can answer before it sees the state. They’re the same design, applied to opposite ends of the model.
Claude Code Session Compaction in 2026: How Context Summarization Works and What Your Agent...
This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content ...