Skip to content

Discover

Find tools for your stack. Pick an audience — we handle the noise.

Discover picks for AI Agents & Assistants

See all tools in AI Agents & Assistants →

On Hacker News

Ranked by discussion

See all →
  1. 5dive

    Healthy
    100
  2. Agent AFK

    Coding-agent harness built for unattended, away-from-keyboard runs across four surfaces sharing one session manager: one-shot CLI, REPL, cron-friendly headless daemon, and a Telegram bot. Editable agent loop (prompts, permission gates, model routing, explicit terminal states), MCP (stdio/HTTP/SSE + OAuth), lifecycle hooks, background subagents, plan mode, cross-session memory, and an append-only trace receipt (`afk trace show`). Works with Anthropic and any OpenAI-compatible endpoint (GPT, Codex, local MLX/llama.cpp/Ollama)

    Healthy
    81
  3. Cybara

    Healthy
    57
  4. Talon

    Healthy
    36
  5. Hephaestus

    Open Agent OS for Claude Code, Codex, and Cursor with a meta-agent builder, A2A Hub routing, local ontology, and memory/security gates. Apache-2.0.

    Healthy
    34
  6. LIA

    Healthy
    25
  7. Proliferate

    Open-source local and cloud agent IDE for Claude Code, Codex, Gemini CLI, OpenCode, and similar coding agents; parallel workspaces, subagents, plugins, MCP, and review/merge flow around real CLI sessions.

    Healthy
    24
  8. l33tdawg/sage

    Institutional memory for AI agents with real BFT consensus. 4 application validators vote on every memory before it's committed — no more storing garbage. 13 MCP tools, runs locally, works with any MCP-compatible model. Backed by 4 published research papers.

    Healthy
    23
  9. claude-flow

    Deploy multi-agent swarms with coordinated workflows.

    Healthy
    22
  10. VT Code

    Healthy
    20
  11. sheawinkler/ContextLattice

    Private-by-default memory and context layer for agents with Go/Rust runtime, staged retrieval across fused data backends, and long-horizon context continuity.

    Healthy
    18
  12. Loki Mode

    Multi-agent autonomous SDLC framework. Spec to deployed app. PRD, GitHub issue, OpenAPI/JSON/YAML, or one-line brief. 5 AI providers, 11 quality gates.

    Healthy
    18

New this week

See all →

Beta — feedback welcome: [email protected]