Nasiko: The Open Runtime for AI Agents (10k stars)
What it does
All text below is quoted directly from the project README.
>The Open Runtime for AI Agents
Features:
- LLM Router: Agents get an OPENAI_BASE_URL and a short-lived identity token instead of a real key. The router resolves provider, model, and key server-side. No agent and no log ever sees a real API key.
- Cost and token attribution: Usage and cost are collected from gen_ai.* span attributes and broken out per agent and per model, rather than arriving as a single provider invoice you have to reverse-engineer.
- One trace per interaction: Every dispatch and proxy hop emits a real OTel span, so a request is one end-to-end trace across every agent hop, with cost attached.
- MCP Gateway: One permanent URL gives every agent a merged, permission-filtered view of Composio toolkits and custom MCP servers, without the agent ever holding the credentials. An agent discovers only what it was granted.
- Flow guards: Redis-backed cascade limits (depth, fan-out, token budget, timeout, cycle detection) stop a loop between two agents from quietly consuming your budget.
- Encrypted secrets: Per-agent secrets are encrypted at rest with AES-256-GCM and injected only at deploy time, so they stay out of your repo.
- Deploy anything that speaks A2A: nasiko deploy builds, pushes to the embedded registry, and runs it. No external registry required, and no SDK to adopt.
- Intelligent routing engine: A 3-stage pipeline: shortlist by embedding similarity, rerank on conversation context, then an LLM makes the final pick. Callers do not need to know your fleet.
>nasiko agents discover reads your machine, prints what it finds, and exits.
Repository
Nasiko-Labs/nasiko
Repository stats
|Metric|Value|
|:-|:-|
|Stars|10,633|
|Forks|2.6k|
|Last release|v1.0.0 (2026-02-12)|
|Languages|Rust 53.7%, TypeScript 37.1%, Python 7.3%|
|Contributors|35|
|AI contributor accounts (Claude / Codex / Cursor / Copilot)|@claude (127 commits), @Copilot (31 commits), @cursoragent (2 commits)|
|AI co-authored commits|Claude: 420, Cursor: 2, Copilot: 52|
Main contributor
|Field|Value|
|:-|:-|
|GitHub|@nasiko-neeraj|
|Commits to this repo|286 (top contributor)|
|Followers|26|
──────────────────────────────
📌 If you want to browse more repos like this, we've organized them by category and rankings here: bestgithubrepositories.com
🗂️ We're also archiving repos where possible, so useful projects don't disappear when they're removed from GitHub.
2 points
Mentions
Nasiko: The Open Runtime for AI Agents (10k stars) What it does All text below is quoted directly from the project README. >The Open Runtime for AI Agents Features: - LLM Router: Agents get an OPENAI_BASE_URL and a short-lived identity token instead of a real key. The router resolves provider, model, and key server-side. No agent and no log ever sees a real API key. - Cost and token attribution: Usage and cost are collected from gen_ai.* span attributes and broken out per agent and per model, rather than arriving as a single provider invoice you have to reverse-engineer. - One trace per interaction: Every dispatch and proxy hop emits a real OTel span, so a request is one end-to-end trace across every agent hop, with cost attached. - MCP Gateway: One permanent URL gives every agent a merged, permission-filtered view of Composio toolkits and custom MCP servers, without the agent ever holding the credentials. An agent discovers only what it was granted. - Flow guards: Redis-backed cascade limits (depth, fan-out, token budget, timeout, cycle detection) stop a loop between two agents from quietly consuming your budget. - Encrypted secrets: Per-agent secrets are encrypted at rest with AES-256-GCM and injected only at deploy time, so they stay out of your repo. - Deploy anything that speaks A2A: nasiko deploy builds, pushes to the embedded registry, and runs it. No external registry required, and no SDK to adopt. - Intelligent routing engine: A 3-stage pipeline: shortlist by embedding similarity, rerank on conversation context, then an LLM makes the final pick. Callers do not need to know your fleet. >nasiko agents discover reads your machine, prints what it finds, and exits. Repository Nasiko-Labs/nasiko Repository stats |Metric|Value| |:-|:-| |Stars|10,633| |Forks|2.6k| |Last release|v1.0.0 (2026-02-12)| |Languages|Rust 53.7%, TypeScript 37.1%, Python 7.3%| |Contributors|35| |AI contributor accounts (Claude / Codex / Cursor / Copilot)|@claude (127 commits), @Copilot (31 commits), @cursoragent (2 commits)| |AI co-authored commits|Claude: 420, Cursor: 2, Copilot: 52| Main contributor |Field|Value| |:-|:-| |GitHub|@nasiko-neeraj| |Commits to this repo|286 (top contributor)| |Followers|26| ────────────────────────────── 📌 If you want to browse more repos like this, we've organized them by category and rankings here: bestgithubrepositories.com 🗂️ We're also archiving repos where possible, so useful projects don't disappear when they're removed from GitHub.
Nasiko-Labs / nasiko: The Open Runtime for AI Agents ★10636 Nasiko-Labs/nasiko
@nasikolabs I gave a workshop about their really amazing open source agent runtime, was blown away by the feature set. In minutes, you can see where every token goes. If you use their built in router, you can hot swap the model in your existing coding agents. Nasiko-Labs/nasiko