Parallax – Coordinate adversarial AI agents over durable streams
Parallax is a CLI for orchestrating independent AI agent cohorts (Claude, Codex, etc.) over isolated, append-only logs or streams. Each cohort operates on its own log and does not see the intermediate reasoning of others i.e. disagreement is enforced at the infrastructure layer rather than prompted at runtime. Agents write to sequenced, durable logs and a separate moderator agent subscribes to all streams, monitors progress, issues steering instructions when necessary, and synthesizes outputs at the end. That means, coordination is just done over a log with natural language, which allows us…
Parallax – Coordinate adversarial AI agents over durable streams launched on March 2, 2026 with 5 votes, #1,928 of 23,380 launches that month and more than 75% of that year's launches.
What it does
Distributed multi-agent research engine with dynamic strategy planning, durable stream-based coordination, and controlled synthesis - s2-streamstore/parallax
Multi-agent research on S2 streams for independent reasoning and structured convergence. Note: This is a vibecoded proof of concept. Expect rough edges. Most AI research tools run one model, in one context, asking itself to consider multiple perspectives. Parallax spawns independent agent cohorts on isolated S2 streams. Each group reasons without seeing what the others are doing, then synthesizes after the fact. S2 streams can be dynamically created to execute any reasoning strategy. Get an S2 access token (it's free) from s2.dev/dashboard and create a basin. cargo build --release cp target/release/parallax ~ /.local/bin/parallax Configure: mkdir -p ~ /.config/parallax cat > ~…from github.com
In the maker’s words, at launch
Parallax is a CLI for orchestrating independent AI agent cohorts (Claude, Codex, etc.) over isolated, append-only logs or streams. Each cohort operates on its own log and does not see the intermediate reasoning of others i.e. disagreement is enforced at the infrastructure layer rather than prompted at runtime. Agents…
Does a similar job
all alternatives →
Parallax by GradientOct 2025 · github.com · ▲334Host LLMs across devices sharing GPU to make your AI go brrr
ParallaxMar 2026 · parallax.maxigimenez.xyz · ▲109Local-first AI orchestrator for software development tasks.
Progress AI ObservabilityAug 2026 · telerik.com · ▲168Hi HN! We’re the team behind Fiddler, and we recently built an Agent Cache feature. It works by capturing an LLM request/response pair and, once caching is enabled, serving subsequent matching calls locally so duplicate requests never hit the provider. It’s meant to reduce three pains that show up together in agent development: token cost, feedback-loop latency, and output non-determinism. We’d love to hear your thoughts.
20+ Claude Code agents coordinating on real work (open source)Feb 2026 · github.com · ▲53Single-agent LLMs suck at long-running complex tasks. We’ve open-sourced a multi-agent orchestrator that we’ve been using to handle long-running LLM tasks. We found that single LLM agents tend to stall, loop, or generate non-compiling code, so we built a harness for agents to coordinate over shared context while work is in progress. How it works: 1. Orchestrator agent that manages task decomposition 2. Sub-agents for parallel work 3. Subscriptions to task state and progress 4. Real-time sharing of intermediate discoveries between agents We tested this on a Putnam-level math problem, but the…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 21d ago · stillwet.art
FastRouter.ai▲364Route requests to the right LLM for cost, latency & quality
AI · 22d ago · fastrouter.ai
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
Littlebird▲709Littlebird remembers everything across your meetings, messages, docs, and apps, then takes action so you can recall any detail and never lose context.
AI · Mar 2026 · littlebird.ai
